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

    Neuronpedia

    INDEX
    Explanations

    class definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    в
    1.37
    н
    1.30
    му
    1.29
    м
    1.27
    Појединачна
    1.26
     दक्ष
    1.22
    тин
    1.22
    我相信
    1.21
    atma
    1.21
    ваний
    1.20
    POSITIVE LOGITS
    ب
    1.72
     harnessed
    1.52
    튿
    1.45
    ീക
    1.45
    swer
    1.37
    sah
    1.37
    nese
    1.36
    مع
    1.36
    swick
    1.34
     insist
    1.30
    Act Density 0.004%

    No Known Activations