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

    Neuronpedia

    INDEX
    Explanations

    foreign language words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ilih
    0.48
     större
    0.46
     verdens
    0.44
     brauchen
    0.43
     ਵਿਚ
    0.43
    ading
    0.41
    ylum
    0.41
     கூறு
    0.41
     अवलंब
    0.41
     peluang
    0.41
    POSITIVE LOGITS
     сведения
    0.49
     Sólo
    0.49
    ק
    0.47
     salted
    0.45
     Сер
    0.44
     Alumin
    0.44
     contato
    0.43
     Método
    0.42
    órios
    0.42
    नाइट
    0.41
    Act Density 0.001%

    No Known Activations