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

    Neuronpedia

    INDEX
    Explanations

    digits and integers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (rx
    -0.09
    สนาม
    -0.08
    slick
    -0.08
    (gray
    -0.08
     свет
    -0.08
     rivalry
    -0.08
    asuring
    -0.08
     мировой
    -0.08
     sidewalks
    -0.08
     beaux
    -0.08
    POSITIVE LOGITS
    骰
    0.09
    组合
    0.09
     aliqu
    0.08
     multiplic
    0.08
     dice
    0.08
     odds
    0.08
     distribut
    0.08
     Factors
    0.08
     factors
    0.08
    .product
    0.08
    Act Density 0.024%

    No Known Activations