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

    Neuronpedia

    INDEX
    Explanations

    punishment as per laws

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     as
    0.49
     arte
    0.46
     للط
    0.40
     artistic
    0.39
     surprising
    0.39
     Andean
    0.39
     corre
    0.39
     äußer
    0.39
     كيف
    0.38
     Ris
    0.38
    POSITIVE LOGITS
    तो
    0.47
    ร้อม
    0.46
    प्ता
    0.45
     खिताब
    0.44
    超過
    0.43
    Если
    0.43
    шение
    0.43
    hoog
    0.43
    螓
    0.42
    magic
    0.42
    Act Density 0.003%

    No Known Activations