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

    Neuronpedia

    INDEX
    Explanations

    numbers, N, K

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ссылки
    0.82
    ן
    0.78
    the
    0.74
    ды
    0.73
     выглядит
    0.73
     пи
    0.72
     Архиви
    0.72
    ayv
    0.71
     لوگ
    0.71
     ਬ
    0.71
    POSITIVE LOGITS
     décider
    0.79
     généraux
    0.73
    ératures
    0.73
     género
    0.72
     Estudios
    0.72
     Pyrénées
    0.72
     Nationality
    0.71
    ][/
    0.70
     syair
    0.70
     travaux
    0.69
    Act Density 0.000%

    No Known Activations