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

    Neuronpedia

    INDEX
    Explanations

    +

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PSD
    -0.07
    Employee
    -0.06
     law
    -0.06
     caval
    -0.06
     항
    -0.06
    emy
    -0.06
    _reward
    -0.06
     Force
    -0.06
    .tensor
    -0.06
    Extent
    -0.06
    POSITIVE LOGITS
    yii
    0.07
    $array
    0.07
    assandra
    0.07
     отказ
    0.07
    copies
    0.06
    PositiveButton
    0.06
    aimassage
    0.06
    줄
    0.06
     Suc
    0.06
    .Fail
    0.06
    Act Density 0.014%

    No Known Activations