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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    添加
    -0.07
     boca
    -0.07
     المف
    -0.06
     boosting
    -0.06
    -color
    -0.06
    .Strict
    -0.06
    $value
    -0.06
     jsx
    -0.06
    div
    -0.06
    staticmethod
    -0.06
    POSITIVE LOGITS
     jap
    0.07
    _MATH
    0.07
    ewn
    0.07
     locking
    0.06
     adorn
    0.06
     disappear
    0.06
     jac
    0.06
     спів
    0.06
     iVar
    0.06
    ーティ
    0.06
    Act Density 0.004%

    No Known Activations