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

    Neuronpedia

    INDEX
    Explanations

    static or public

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    饔
    -0.07
     pants
    -0.07
     새
    -0.07
    经贸
    -0.06
     Allison
    -0.06
    קשה
    -0.06
    照料
    -0.06
    ԃ
    -0.06
    뼝
    -0.06
    Ｏ
    -0.06
    POSITIVE LOGITS
    genre
    0.08
    requency
    0.07
     Decimal
    0.07
    行业的
    0.07
    figures
    0.07
    вшей
    0.07
    ocol
    0.07
    Level
    0.07
    шед
    0.07
    �
    0.07
    Act Density 0.006%

    No Known Activations