Neel Nanda

British AI safety researcher; Staff Research Scientist at Google DeepMind, where he leads the mechanistic interpretability team. He studied mathematics at the University of Cambridge (BA, 2020), after which he spent a gap year exploring AI safety through internships at the Future of Humanity Institute, DeepMind, and the Centre for Human-Compatible AI at UC Berkeley, before taking quantitative finance internship roles at Jane Street and Jump Trading.

He joined Anthropic as a language-model interpretability researcher under Chris Olah, then moved to Google DeepMind in 2022 to build and lead their mechanistic interpretability group. He created TransformerLens, a widely-used open-source library for studying the internal computations of language models, and runs a technical blog and YouTube channel on mechanistic interpretability research. In 2023 MIT Technology Review named him to its Innovators Under 35 list.

On 4 June 2024 he was one of seven researchers to sign "A Right to Warn about Advanced Artificial Intelligence" by name — alongside Jacob Hilton, Daniel Kokotajlo, Ramana Kumar, William Saunders, Carroll Wainwright, and Daniel Ziegler — and the only named current Google DeepMind employee among them. The letter, also endorsed by Geoffrey Hinton, Yoshua Bengio, and Stuart Russell, demanded structural whistleblower protections inside frontier-AI companies. The event is documented in the Right to Warn open letter event and the insider whistleblowing from frontier labs strategy entry.