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

    Neuronpedia

    INDEX
    Explanations

    serif; or serif fonts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ك
    0.77
    ta
    0.71
    6
    0.68
    9
    0.66
    7
    0.66
    K
    0.65
    An
    0.64
    Id
    0.63
    St
    0.63
    ty
    0.62
    POSITIVE LOGITS
     των
    0.69
     svega
    0.68
     svom
    0.67
     veoma
    0.67
     Хабаров
    0.67
    jų
    0.65
    ја
    0.64
     esos
    0.63
     მიმოწერა
    0.63
     گئی
    0.62
    Act Density 0.003%

    No Known Activations