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

    Neuronpedia

    INDEX
    Explanations

    module

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    division
    -0.08
    ,h
    -0.08
     anak
    -0.07
    _DI
    -0.07
     значение
    -0.07
    *L
    -0.07
    �
    -0.07
    :L
    -0.07
    .managed
    -0.06
     Derrick
    -0.06
    POSITIVE LOGITS
     unsettling
    0.07
    __));↵
    0.07
    军
    0.07
    实事求是
    0.06
    冷漠
    0.06
    频率
    0.06
    (...
    0.06
     endors
    0.06
    ӧ
    0.06
     Pilot
    0.06
    Act Density 0.007%

    No Known Activations