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

    Neuronpedia

    INDEX
    Explanations

    calculate

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    皭
    -0.08
    :inline
    -0.08
    機構
    -0.08
     Gab
    -0.07
    vtColor
    -0.07
    列为
    -0.07
    tü
    -0.07
    _ACTIVITY
    -0.07
    toa
    -0.06
    矍
    -0.06
    POSITIVE LOGITS
     Cypress
    0.07
    バ
    0.07
    スキル
    0.07
     goats
    0.07
    ipes
    0.07
     sims
    0.06
    مشاريع
    0.06
    fruit
    0.06
     יוכל
    0.06
    hare
    0.06
    Act Density 0.017%

    No Known Activations