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

    Neuronpedia

    INDEX
    Explanations

    remote desktop services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ل
    0.84
    ล
    0.83
    _
    0.83
     I
    0.82
    .
    0.82
    é
    0.79
     as
    0.78
     Interesting
    0.77
    什么
    0.75
    [
    0.74
    POSITIVE LOGITS
    ﺪ
    0.85
    ної
    0.84
     рэгістра
    0.82
    ਦੀ
    0.82
    ުރ
    0.80
    دی
    0.79
     tıkl
    0.77
    า
    0.77
     όχι
    0.76
    ﺮ
    0.76
    Act Density 0.001%

    No Known Activations