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

    Neuronpedia

    INDEX
    Explanations

    bit precision

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ى
    0.57
    nobyl
    0.50
    一群
    0.48
    닙
    0.48
    نی
    0.47
     لمبے
    0.47
     diciamo
    0.47
     acknowled
    0.47
    人都
    0.46
     항상
    0.46
    POSITIVE LOGITS
    Market
    0.75
    Seattle
    0.73
    Level
    0.73
    Salt
    0.73
    Content
    0.72
    WATER
    0.71
    ك
    0.70
    1
    0.70
    AR
    0.69
    ES
    0.69
    Act Density 0.003%

    No Known Activations