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

    Neuronpedia

    INDEX
    Explanations

    building and context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     khách
    0.48
     ডেপু
    0.48
    ﺵ
    0.47
     profiss
    0.47
     cấp
    0.46
     Такие
    0.46
     probative
    0.46
     có
    0.45
    ждая
    0.45
    ด
    0.45
    POSITIVE LOGITS
     annealed
    0.44
    cka
    0.44
     i
    0.44
    ;</
    0.43
    bron
    0.43
    ത്തിനും
    0.43
    mu
    0.43
    uclear
    0.42
    Tagged
    0.41
    ml
    0.41
    Act Density 0.002%

    No Known Activations