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

    Neuronpedia

    INDEX
    Explanations

    verbs and their endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     with
    0.28
     يف
    0.25
     dùng
    0.25
    0.25
     باستخدام
    0.25
     المناطق
    0.25
     utilising
    0.24
     تركيب
    0.24
     делаю
    0.24
     from
    0.24
    POSITIVE LOGITS
    ੋ
    0.27
    お
    0.26
    ро
    0.24
    R
    0.23
    이
    0.23
    ático
    0.23
    ᱛ
    0.22
    تر
    0.22
    ම
    0.22
    म
    0.22
    Act Density 0.131%

    No Known Activations