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

    Neuronpedia

    INDEX
    Explanations

    being or quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     εύ
    0.44
     trafficking
    0.43
     эпи
    0.40
    ’
    0.40
    рования
    0.39
    terbury
    0.39
     ресурсов
    0.39
    ρε
    0.38
    raisers
    0.38
    自身的
    0.38
    POSITIVE LOGITS
    an
    0.67
    ان
    0.52
     akt
    0.50
     gaw
    0.48
    റുണ്ട്
    0.48
    ي
    0.46
    浙
    0.46
    actor
    0.46
    another
    0.46
     voulu
    0.45
    Act Density 0.002%

    No Known Activations