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

    Neuronpedia

    INDEX
    Explanations

    collocations with specific nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ك
    0.96
    ر
    0.91
    ม
    0.90
    ب
    0.89
     of
    0.89
    ق
    0.87
    1
    0.82
    д
    0.80
    기
    0.77
    r
    0.77
    POSITIVE LOGITS
    .
    0.77
    <0x89>
    0.73
    ‌پ
    0.67
    <0x8A>
    0.66
    <0xAC>
    0.64
    س
    0.64
     profane
    0.63
    <0x91>
    0.62
    />
    0.62
    yn
    0.61
    Act Density 0.056%

    No Known Activations