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

    Neuronpedia

    INDEX
    Explanations

    board game components

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hello
    -0.09
     metabolism
    -0.08
    aism
    -0.08
    望
    -0.08
     Augustine
    -0.07
    怀
    -0.07
     aprendizado
    -0.07
    哲
    -0.07
    继
    -0.07
     contemplating
    -0.07
    POSITIVE LOGITS
    رقام
    0.09
     Labels
    0.08
     terdiri
    0.08
     nummers
    0.08
     표시
    0.08
     collectibles
    0.08
     комплект
    0.08
    عداد
    0.08
    ilala
    0.08
     خلکو
    0.08
    Act Density 0.010%

    No Known Activations