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

    Neuronpedia

    INDEX
    Explanations

    wide range

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ਨੀ
    0.94
    िटेशन
    0.92
     పూర్తిగా
    0.92
    <unused430>
    0.89
    अधिक
    0.88
     ज्यादा
    0.87
    ής
    0.86
     суда
    0.85
    िनेट
    0.84
     fondly
    0.83
    POSITIVE LOGITS
     range
    1.57
     ranging
    1.48
    ranging
    1.46
     spectrum
    1.41
     variety
    1.41
     спект
    1.32
    范围
    1.25
    範圍
    1.23
    range
    1.23
    範囲
    1.23
    Act Density 0.075%

    No Known Activations