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

    Neuronpedia

    INDEX
    Explanations

    score

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ingin
    -0.07
     QDir
    -0.07
     حی
    -0.06
    ipur
    -0.06
    nton
    -0.06
     bor
    -0.06
     Bren
    -0.06
     مز
    -0.06
    361
    -0.06
     quang
    -0.06
    POSITIVE LOGITS
    َج
    0.07
    mA
    0.07
    "]->
    0.07
     �
    0.06
     TextStyle
    0.06
    /grpc
    0.06
     tưởng
    0.06
    _CONSTANT
    0.06
    Att
    0.06
    ."""↵
    0.06
    Act Density 0.003%

    No Known Activations