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

    Neuronpedia

    INDEX
    Explanations

    if anything

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    обы
    1.05
    домо
    1.02
     ﺍﻟ
    1.00
     possibilidades
    0.99
     quantidades
    0.98
     terceira
    0.98
     только
    0.97
     tradicionales
    0.97
     Мы
    0.97
     первая
    0.97
    POSITIVE LOGITS
    ,
    0.83
     Stati
    0.82
    adon
    0.80
    enzi
    0.79
    om
    0.72
    itas
    0.72
    inaria
    0.72
    ías
    0.70
    name
    0.69
    in
    0.69
    Act Density 0.000%

    No Known Activations