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

    Neuronpedia

    INDEX
    Explanations

    sidesdifference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ؛
    0.44
     CIRCU
    0.41
     ویکی‌پ
    0.41
    ۆر
    0.41
    ؛
    0.41
    чиго
    0.41
     поддержки
    0.40
     аллер
    0.40
     которыми
    0.40
     "_"
    0.40
    POSITIVE LOGITS
     annual
    0.40
    -
    0.39
    Coat
    0.39
     prettier
    0.39
     bigger
    0.39
    kovic
    0.37
     worth
    0.37
    biased
    0.37
    kel
    0.37
    worth
    0.36
    Act Density 0.000%

    No Known Activations