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

    Neuronpedia

    INDEX
    Explanations

    become popular or important

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ма
    2.34
    }$.,
    2.11
    ती
    2.08
     racionais
    2.08
    Př
    2.06
    ك
    2.03
    ны
    1.94
     impulsar
    1.93
    پ
    1.90
    í
    1.87
    POSITIVE LOGITS
    enite
    1.71
    le
    1.68
    ist
    1.68
    et
    1.64
    lič
    1.61
    bar
    1.58
    !\!\
    1.57
     extinct
    1.56
    leit
    1.56
    ową
    1.55
    Act Density 0.156%

    No Known Activations