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

    Neuronpedia

    INDEX
    Explanations

    news reports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ath
    -0.06
     gift
    -0.06
    daf
    -0.06
     mattered
    -0.05
    стин
    -0.05
    <File
    -0.05
    غاز
    -0.05
     Çalış
    -0.05
    Cop
    -0.05
    ycl
    -0.05
    POSITIVE LOGITS
     moderation
    0.07
    .MON
    0.07
    /Admin
    0.07
    UAGE
    0.06
    ़े
    0.06
    getStyle
    0.06
    २
    0.06
     vàng
    0.06
     wireType
    0.06
    KC
    0.06
    Act Density 0.111%

    No Known Activations