213▼4
Neel Nanda
@NeelNanda5AI Safety9.0
389
top followers
40.3K
followers
389
top followers
40.3K
followers
Mechanistic Interpretability lead DeepMind. Formerly @AnthropicAI, independent. In this to reduce AI X-risk. Neural networks can be understood, let's go do it!
AI Classification
Neel Nanda leads the mechanistic interpretability team at DeepMind, focusing on reverse-engineering neural networks to reduce AI existential risk. Formerly at Anthropic. Tagged AI Safety because >=60% of his public output centers on alignment, interpretability, and governance work.
Top followers
Public AI-ranked followers appear first; other tracked followers remain below.
Last updated 15d ago · 1989 influencers tracked · 3000 ranked users
