AI Safety and Mechanistic Interpretability Expert
in
AnthropicAssociated BrandNeel Nanda is an AI Safety and Mechanistic Interpretability Expert, ranked #2 in Tech & Software (AI & ML Researchers) (Top 8%).
Last updated
Neel Nanda is a leading figure in AI safety and mechanistic interpretability, currently heading the Mechanistic Interpretability team at DeepMind. He focuses on reducing AI existential risks by understanding neural networks. His content includes educational posts, research updates, and insights into AI safety, often shared on Twitter and YouTube. He collaborates with academic institutions and AI organizations, emphasizing rigorous scientific methods and practical applications of interpretability research.
Neural networks can be understood, let's go do it!
Favikon helps you find the right creators, analyze them in depth, reach out at scale, and track what works.
India
