Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    cooking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Detect
    -0.07
     변수
    -0.07
    inus
    -0.07
     Water
    -0.06
     water
    -0.06
     dataSource
    -0.06
     включ
    -0.06
     RIGHTS
    -0.06
     pill
    -0.06
    Engine
    -0.06
    POSITIVE LOGITS
     travers
    0.08
     strained
    0.07
    Ask
    0.07
     sieve
    0.07
    _agents
    0.06
     Trie
    0.06
    -Out
    0.06
    全部
    0.06
     gossip
    0.06
     탈
    0.06
    Act Density 0.003%

    No Known Activations