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

    Neuronpedia

    INDEX
    Explanations

    impose rules or order

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Η
    1.66
     poin
    1.62
     maw
    1.54
    десят
    1.54
    Η
    1.50
     EP
    1.48
     comet
    1.48
     pore
    1.48
    িগ
    1.46
     Section
    1.45
    POSITIVE LOGITS
    ی
    2.55
    ق
    2.14
    л
    2.09
    ش
    2.03
    ج
    1.97
    ità
    1.94
    ী
    1.93
    та
    1.91
    いない
    1.91
    بی
    1.91
    Act Density 0.013%

    No Known Activations