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

    Neuronpedia

    INDEX
    Explanations

    import sys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ing
    0.85
     The
    0.78
    Means
    0.77
    の間
    0.77
    િ
    0.77
    ש
    0.76
    t
    0.75
    ı
    0.75
     (
    0.74
    =\
    0.74
    POSITIVE LOGITS
     sys
    0.67
    งาน
    0.65
     модуля
    0.63
     glared
    0.62
     obesidad
    0.61
     énorm
    0.61
     juncture
    0.60
     rám
    0.59
     컬러
    0.59
     ۴
    0.59
    Act Density 0.004%

    No Known Activations