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

    Neuronpedia

    INDEX
    Explanations

    code symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    giene
    -0.07
    -sup
    -0.07
    pleado
    -0.06
    อให
    -0.06
     البي
    -0.06
     Distribution
    -0.06
     cháy
    -0.06
    baar
    -0.06
    爷
    -0.06
    sell
    -0.06
    POSITIVE LOGITS
     Undo
    0.07
     Вот
    0.06
     �
    0.06
    Fish
    0.06
     输出
    0.05
     eg
    0.05
    оды
    0.05
     glimpse
    0.05
     LEGO
    0.05
    _equ
    0.05
    Act Density 0.034%

    No Known Activations