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

    Neuronpedia

    INDEX
    Explanations

    last

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     הגדול
    -0.08
    /pages
    -0.08
    érêt
    -0.08
     cartes
    -0.08
    合理
    -0.07
     diariamente
    -0.07
     ಹಾಕ
    -0.07
     racional
    -0.07
    riti
    -0.07
    ñs
    -0.07
    POSITIVE LOGITS
     week
    0.24
     year
    0.23
     month
    0.23
    year
    0.20
     વર્ષે
    0.19
    week
    0.19
     సంవత్స
    0.18
     Woche
    0.18
    _year
    0.18
    month
    0.17
    Act Density 0.048%

    No Known Activations