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

    Neuronpedia

    INDEX
    Explanations

    expert [role]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    णिज्य
    2.22
    ্ক
    1.73
     haut
    1.66
    بيقات
    1.62
     tách
    1.61
    helf
    1.59
     احنا
    1.59
    seguir
    1.58
    雑貨
    1.57
    色列
    1.57
    POSITIVE LOGITS
    ה
    2.18
    ๐
    2.00
    স
    1.83
    ل
    1.73
     phenols
    1.73
    া
    1.70
    vorm
    1.64
    لک
    1.64
    reich
    1.63
     হবেন
    1.60
    Act Density 0.002%

    No Known Activations