Mechanistic Interpretability lead DeepMind. Formerly @AnthropicAI, independent. In this to reduce AI X-risk. Neural networks can be understood, let's go do it!
Neel Nanda leads Google DeepMind's mechanistic interpretability team, researching neural network understanding to reduce AI x-risk. Formerly at Anthropic. Primary public identity is AI safety research.
Showing only followers who are currently ranked in the top 1000.
Last updated — · 1040 influencers tracked · 2000 ranked users