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

    Neuronpedia

    INDEX
    Explanations

    percentages and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    о
    0.95
    ası
    0.82
    يم
    0.75
    र
    0.73
    ح
    0.73
    یک
    0.73
    ா
    0.72
    arı
    0.71
    الح
    0.71
    кін
    0.70
    POSITIVE LOGITS
     inade
    0.87
     Vivi
    0.83
     Varan
    0.82
     PPC
    0.80
     AII
    0.79
    ((\
    0.77
    ̾
    0.76
     성장
    0.75
    িনবার্গ
    0.75
    kval
    0.75
    Act Density 0.000%

    No Known Activations