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

    Neuronpedia

    INDEX
    Explanations

    proportion or estimation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    成年
    0.67
     saturation
    0.63
     overtake
    0.62
     saturate
    0.61
    が高
    0.60
    हाई
    0.59
     shakes
    0.59
     adulta
    0.58
    מח
    0.57
     appartenant
    0.57
    POSITIVE LOGITS
     プラス
    0.82
    時尚
    0.81
    緞
    0.75
    Registry
    0.74
     Zodiac
    0.74
     Fuzzy
    0.73
     .+
    0.73
    $+
    0.72
    +
    0.71
    .+
    0.70
    Act Density 0.137%

    No Known Activations