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

    Neuronpedia

    INDEX
    Explanations

    brand and product names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     غیر
    0.19
    Boxes
    0.19
     يت
    0.18
    ையைக்
    0.18
     بعض
    0.17
     sommet
    0.17
    ிகளைக்
    0.17
     ایسے
    0.17
     минимум
    0.17
     Schum
    0.17
    POSITIVE LOGITS
    ’
    0.26
     adlı
    0.21
    ?
    0.20
    ﾕ
    0.19
    angnya
    0.19
    ”,
    0.19
    ului
    0.19
    ̣
    0.18
     महज
    0.18
    ?,
    0.18
    Act Density 0.950%

    No Known Activations