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

    Neuronpedia

    INDEX
    Explanations

    Hitler's actions and events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    る
    1.00
    ی
    0.98
    s
    0.87
    ט
    0.87
    ти
    0.83
    ים
    0.80
    تی
    0.79
     imbalances
    0.78
    تها
    0.77
    d
    0.77
    POSITIVE LOGITS
    6
    0.82
    ove
    0.74
    az
    0.68
     Hitler
    0.67
    chen
    0.65
    obe
    0.63
    zinho
    0.63
    iste
    0.61
     desolate
    0.61
     કોઈપણ
    0.61
    Act Density 0.001%

    No Known Activations