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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _checksum
    -0.07
    -background
    -0.07
     Dispatcher
    -0.07
    Spread
    -0.06
     ACTIONS
    -0.06
    community
    -0.06
    CHAIN
    -0.06
    gaard
    -0.06
     deleteUser
    -0.06
    [next
    -0.06
    POSITIVE LOGITS
    (platform
    0.07
    �다
    0.07
     membranes
    0.07
     参数
    0.06
     philosophers
    0.06
    прав
    0.06
    .)↵↵↵↵
    0.06
    slt
    0.06
    /.↵↵
    0.06
     установки
    0.06
    Act Density 0.001%

    No Known Activations