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

    Neuronpedia

    INDEX
    Explanations

    import statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    0.32
     какой
    0.31
     Какой
    0.30
     какого
    0.30
     быть
    0.29
    !
    0.29
     данного
    0.29
     prepd
    0.29
    )
    0.28
    ם
    0.28
    POSITIVE LOGITS
    のアレンジ
    0.32
     phenomenology
    0.31
     använder
    0.30
     remix
    0.29
    emoji
    0.29
    hô
    0.29
     antaranya
    0.29
    他的
    0.28
     monastic
    0.28
     experimental
    0.28
    Act Density 0.014%

    No Known Activations