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

    Neuronpedia

    INDEX
    Explanations

    gun violence unmatched

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     renowned
    0.45
    они
    0.43
     условии
    0.43
     constantly
    0.41
    кова
    0.41
    as
    0.41
    ায়
    0.41
    ন্তু
    0.40
    ર
    0.40
     tgt
    0.39
    POSITIVE LOGITS
     możli
    0.49
     pouvaient
    0.49
    力和
    0.45
     colère
    0.45
     poderia
    0.44
    爆炸
    0.44
     bezpośred
    0.44
     enfl
    0.44
     πρώτη
    0.44
     espont
    0.44
    Act Density 0.002%

    No Known Activations