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

    Neuronpedia

    INDEX
    Explanations

    Dialogue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    跨
    -0.09
     bary
    -0.07
     internationale
    -0.07
     axial
    -0.07
     internacionales
    -0.07
     Hill
    -0.07
    -0.07
     thrust
    -0.07
     manawa
    -0.07
    国际
    -0.07
    POSITIVE LOGITS
     vaikka
    0.08
    .answer
    0.08
     ივნის
    0.08
     ივლის
    0.08
     sauces
    0.08
    вари
    0.08
    uutit
    0.08
    хо
    0.08
    "));
↵
↵
    0.08
    #else
    0.08
    Act Density 0.006%
    No Known Activations