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

    Neuronpedia

    INDEX
    Explanations

    want to act or observe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    想定
    0.84
     예상
    0.80
    ினும்
    0.72
    给了
    0.72
    耐心
    0.71
    รา
    0.70
    stehung
    0.69
    一系列
    0.69
    センス
    0.69
     worrying
    0.68
    POSITIVE LOGITS
     seeing
    1.13
     graag
    1.10
     видеть
    1.06
     see
    1.06
     hearing
    1.05
     hear
    1.04
     хочу
    1.02
     справедливо
    1.02
     revenge
    1.00
     получить
    0.98
    Act Density 0.369%

    No Known Activations