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

    Neuronpedia

    INDEX
    Explanations

    arithmetic and code operator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    y
    0.78
    ر
    0.65
    ん
    0.64
    ं
    0.63
    ്രീ
    0.62
    ות
    0.61
    لط
    0.60
    й
    0.60
     maneiras
    0.56
    αν
    0.56
    POSITIVE LOGITS
    ك
    0.77
    outez
    0.66
     এমনকি
    0.63
    idene
    0.62
     می
    0.61
     أيضا
    0.60
     さらに
    0.60
     ي
    0.60
     slurry
    0.60
     بشكل
    0.60
    Act Density 0.062%

    No Known Activations