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

    Neuronpedia

    INDEX
    Explanations

    thank who

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     하는
    0.89
    ્ર
    0.77
     dinosaur
    0.75
     інших
    0.75
     airbags
    0.73
    ）。
    0.72
     जनसंख्या
    0.71
    ।
    0.71
    れ
    0.71
     aument
    0.70
    POSITIVE LOGITS
    at
    0.93
    ير
    0.91
    تون
    0.91
    ه
    0.91
    感谢
    0.89
    ات
    0.87
    es
    0.87
    де
    0.86
    ה
    0.86
    P
    0.82
    Act Density 0.023%

    No Known Activations