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

    Neuronpedia

    INDEX
    Explanations

    generating code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ب
    0.59
    إ
    0.49
    ن
    0.48
    مع
    0.48
    چ
    0.47
    به
    0.47
    各国
    0.47
    Ч
    0.46
    Ш
    0.46
    ッカー
    0.46
    POSITIVE LOGITS
    aua
    0.50
    compliance
    0.49
    ost
    0.49
    ürk
    0.48
     suv
    0.48
    ismillahirrah
    0.48
    ij
    0.48
    aj
    0.48
     suburban
    0.47
     ü
    0.47
    Act Density 0.002%

    No Known Activations