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

    Neuronpedia

    INDEX
    Explanations

    `from_` and `for_` calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ܢܐ
    0.70
     гульнявыя
    0.67
    ennzeichnet
    0.62
    öder
    0.61
    DetailPage
    0.60
    alim
    0.59
     IncludeField
    0.58
    告示
    0.57
     ವಿಧಾನಸಭಾ
    0.57
     குறை
    0.56
    POSITIVE LOGITS
     (
    0.84
    あ
    0.84
    forRoot
    0.79
    จะ
    0.76
     –
    0.74
    ف
    0.72
     à
    0.71
     a
    0.71
    、
    0.69
     that
    0.68
    Act Density 0.000%

    No Known Activations