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

    Neuronpedia

    INDEX
    Explanations

    second

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الأساس
    0.82
     כמה
    0.81
     Нужно
    0.78
    konom
    0.78
    ೊಂದ
    0.76
    齟
    0.76
     angolo
    0.75
     mussten
    0.74
    ي
    0.74
    кла
    0.74
    POSITIVE LOGITS
     chances
    1.01
     Chances
    0.93
    aries
    0.86
    Bon
    0.86
    வரை
    0.86
    arily
    0.81
    ing
    0.80
     fract
    0.80
     impractic
    0.80
     chance
    0.79
    Act Density 0.162%

    No Known Activations