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

    Neuronpedia

    INDEX
    Explanations

    handling web requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     commencé
    0.73
     Formulas
    0.66
     negó
    0.65
    يلي
    0.65
     Chines
    0.65
    zám
    0.64
    ０
    0.61
    r
    0.59
     नाग
    0.59
     проверка
    0.59
    POSITIVE LOGITS
     on
    0.82
     in
    0.74
    IN
    0.71
    AD
    0.70
     as
    0.69
     by
    0.68
    ent
    0.68
    ON
    0.68
    dat
    0.66
    IT
    0.65
    Act Density 0.002%

    No Known Activations