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

    Neuronpedia

    INDEX
    Explanations

    selling books, courses, or jobs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    зья
    0.45
    жек
    0.44
    섯
    0.43
     externalities
    0.41
     İn
    0.41
    вной
    0.41
    in
    0.41
     Fourth
    0.41
     embargo
    0.41
     Пет
    0.40
    POSITIVE LOGITS
     یا
    0.60
     धात
    0.46
     곡
    0.46
     کتاب
    0.46
     فضای
    0.46
     آگے
    0.46
     کے
    0.45
     فرو
    0.45
     چاہئے
    0.45
     أو
    0.45
    Act Density 0.007%

    No Known Activations