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

    Neuronpedia

    INDEX
    Explanations

    not just X, but also Y

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ان
    1.35
    ל
    1.17
    ﯼ
    1.10
     الجديد
    1.05
     definitiva
    1.03
    на
    1.02
    িতে
    0.98
    comer
    0.96
    اب
    0.95
    از
    0.94
    POSITIVE LOGITS
    dır
    1.46
    től
    1.19
    tól
    1.18
    nın
    1.09
     Blanket
    1.07
    kati
    1.07
    こと
    1.06
    dür
    1.06
    zám
    1.05
     foresee
    1.04
    Act Density 0.015%

    No Known Activations