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

    Neuronpedia

    INDEX
    Explanations

    thing place stuff

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     మాత్రమే
    0.65
     उत्तम
    0.59
     모두
    0.52
     포함
    0.50
     saddened
    0.48
     표시
    0.46
     Ирина
    0.46
     ভাবেই
    0.46
    𝘮
    0.46
     Очень
    0.45
    POSITIVE LOGITS
     φο
    0.45
     operates
    0.43
     gets
    0.43
    渗透
    0.43
     fiebre
    0.42
    ’
    0.42
    掸
    0.42
     hardly
    0.41
     penetrates
    0.41
     med
    0.41
    Act Density 0.012%

    No Known Activations