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

    Neuronpedia

    INDEX
    Explanations

    Accented characters and following words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uginosa
    0.61
    тных
    0.60
     فی
    0.56
    clientsdetails
    0.55
     توی
    0.55
     遅く
    0.54
     NONE
    0.53
     بینی
    0.53
     Л
    0.52
    marshalN
    0.52
    POSITIVE LOGITS
    ’
    0.89
    ك
    0.75
    ة
    0.70
    在
    0.67
    ير
    0.64
    يه
    0.63
     في
    0.61
    ين
    0.61
    و
    0.61
    Ö
    0.61
    Act Density 0.065%

    No Known Activations