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

    Neuronpedia

    INDEX
    Explanations

    understand career path

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hukum
    0.46
    یک
    0.45
    ת
    0.42
    وجد
    0.42
     процедуры
    0.42
    順
    0.42
    بط
    0.41
    من
    0.41
     inesper
    0.40
    تس
    0.40
    POSITIVE LOGITS
     À
    0.51
    spath
    0.47
     Artists
    0.46
     artist
    0.45
    merk
    0.43
     Vero
    0.43
     artists
    0.43
     জিন
    0.43
     красиво
    0.43
    attro
    0.43
    Act Density 0.001%

    No Known Activations