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

    Neuronpedia

    INDEX
    Explanations

    maximum or optimized values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    完毕
    0.87
    ByIndex
    0.86
     אם
    0.86
     immense
    0.83
    弄
    0.83
    ವರ
    0.83
     ناحيه
    0.80
    තුව
    0.80
    一下
    0.79
    أت
    0.79
    POSITIVE LOGITS
    िमम
    1.65
    ima
    1.43
    imal
    1.31
     allowable
    1.29
    imized
    1.23
    umum
    1.21
    imiz
    1.20
    IONAL
    1.16
    imo
    1.14
    imize
    1.12
    Act Density 0.131%

    No Known Activations