Nikhil Prakash

(he/him/his)

PhD Student

Nikhil Prakash
  • Machine learning
  • Mechanistic interpretability
  • Natural language processing 
  • MS in Computer Science, Northeastern University
  • BS in Telecommunication Engineering, RV College of Engineering — India 

Nikhil Prakash is a PhD student in the Khoury College of Computer Sciences at Northeastern University, advised by David Bau.

Prakash’s research focuses on uncovering the internal mechanisms of deep neural networks to improve human–AI collaboration and mitigate risks of misalignment. Currently, he is studying cognitive abilities — such as reasoning and theory of mind — in large language and vision models. He has published his work in leading venues, including ICLR, ICML, NeurIPS, IUI, and Computational Linguistics.

Outside of work, Prakash enjoys playing chess and table tennis, watching documentaries and anime, and learning about culture and history.

  • Agents of Chaos

    Citation: Natalie Shapira, Chris Wendler, Avery Yen, Gabriele Sarti, Koyena Pal, Olivia Floody, Adam Belfki, Alexander R. Loftus, Aditya Ratan Jannali, Nikhil Prakash, Jasmine Cui, Giordano Rogers, Jannik Brinkmann, Can Rager, Amir Zur, Michael Ripa, Aruna Sankaranarayanan, David Atkinson, Rohit Gandikota, Jaden Fiotto-Kaufman, EunJeong Hwang, Hadas Orgad, P. Sam Sahil, Negev Taglicht, Tomer Shabtay, Atai Ambus, Nitay Alon, Shiri Oron, Ayelet Gordon-Tapiero, Yotam Kaplan, Vered Shwartz, Tamar Rott Shaham, Christoph Riedl, Reuth Mirsky, Maarten Sap, David Manheim, Tomer Ullman, David Bau. (2026). Agents of Chaos CoRR, abs/2602.20021. https://doi.org/10.48550/arXiv.2602.20021

  • Language Models use Lookbacks to Track Beliefs

    Citation: Nikhil Prakash, Natalie Shapira, Arnab Sen Sharma, Christoph Riedl, Yonatan Belinkov, Tamar Rott Shaham, David Bau, Atticus Geiger. (2025). Language Models use Lookbacks to Track Beliefs CoRR, abs/2505.14685. https://doi.org/10.48550/arXiv.2505.14685

  • MIB: A Mechanistic Interpretability Benchmark

    Citation: Aaron Mueller, Atticus Geiger, Sarah Wiegreffe, Dana Arad, Iván Arcuschin, Adam Belfki, Yik Siu Chan, Jaden Fried Fiotto-Kaufman, Tal Haklay, Michael Hanna , Jing Huang, Rohan Gupta, Yaniv Nikankin, Hadas Orgad, Nikhil Prakash, Anja Reusch, Aruna Sankaranarayanan, Shun Shao, Alessandro Stolfo, Martin Tutek, Amir Zur, David Bau, Yonatan Belinkov. (2025). MIB: A Mechanistic Interpretability Benchmark ICML. https://openreview.net/forum?id=sSrOwve6vb

  • NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals

    Citation: Jaden Fried Fiotto-Kaufman, Alexander Russell Loftus, Eric Todd, Jannik Brinkmann, Koyena Pal, Dmitrii Troitskii, Michael Ripa, Adam Belfki, Can Rager, Caden Juang, Aaron Mueller, Samuel Marks, Arnab Sen Sharma, Francesca Lucchetti, Nikhil Prakash, Carla E. Brodley, Arjun Guha, Jonathan Bell , Byron C. Wallace, David Bau. (2025). NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals ICLR. https://openreview.net/forum?id=MxbEiFRf39