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

    Neuronpedia

    INDEX
    Explanations

    code or logs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Provides
    -0.07
    TextUtils
    -0.07
    .clicked
    -0.07
    实力
    -0.07
    ,value
    -0.07
    随着
    -0.07
    反击
    -0.07
    盘点
    -0.07
     supports
    -0.07
    _ass
    -0.07
    POSITIVE LOGITS
    ᴸ
    0.08
     perish
    0.07
     atheist
    0.07
     nfl
    0.07
    חום
    0.07
    שפיע
    0.07
    だって
    0.06
    isphere
    0.06
    .genre
    0.06
    bsolute
    0.06
    Act Density 0.068%

    No Known Activations