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

    Neuronpedia

    INDEX
    Explanations

    under or less than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hlad
    0.38
     প্রায়
    0.35
    nearly
    0.35
     nearly
    0.34
    ২৭
    0.34
    樹脂
    0.34
    বিভিন্ন
    0.33
    พันธุ์
    0.33
     olika
    0.33
     مشارکت
    0.33
    POSITIVE LOGITS
     threshold
    0.81
     Threshold
    0.72
     thresholds
    0.71
    阈
    0.71
    threshold
    0.71
    Threshold
    0.66
    THRESHOLD
    0.60
     ≤
    0.59
    閾
    0.59
    未満
    0.56
    Act Density 0.074%

    No Known Activations