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

    Neuronpedia

    INDEX
    Explanations

    characters from many languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    0.60
    ur
    0.52
    il
    0.50
    font
    0.49
    t
    0.49
    ville
    0.48
    packing
    0.47
    against
    0.46
    l
    0.46
     packed
    0.46
    POSITIVE LOGITS
    ق
    0.54
    䂺
    0.52
     ACCOUNT
    0.52
    Фі
    0.52
    ﺔ
    0.52
    늙
    0.52
    К
    0.50
     Nw
    0.50
    Ал
    0.49
    Չ
    0.49
    Act Density 0.000%

    No Known Activations