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

    Neuronpedia

    INDEX
    Explanations

    aya, tag, yield, Latina

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TY
    0.81
    STATUS
    0.79
    USING
    0.78
    ATTACH
    0.77
     варианты
    0.76
    SE
    0.75
    BY
    0.75
    UND
    0.73
    TYPES
    0.73
    COMMENT
    0.72
    POSITIVE LOGITS
    除此之外
    1.04
     sensit
    0.89
     преподава
    0.89
    ڪ
    0.88
     👀
    0.87
    ້
    0.87
     coisa
    0.86
    signale
    0.86
    idação
    0.86
    ◽
    0.86
    Act Density 0.002%

    No Known Activations