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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ACS
    -0.07
    Entr
    -0.06
    하우
    -0.06
     société
    -0.06
    _ends
    -0.06
    یده
    -0.06
    SENT
    -0.06
     lekker
    -0.06
    不可
    -0.06
     боли
    -0.06
    POSITIVE LOGITS
     спир
    0.06
     диамет
    0.06
    .Embed
    0.06
     connects
    0.06
    人民共和国
    0.06
     Morrow
    0.06
     mekan
    0.06
     Flex
    0.06
     Ret
    0.06
     Packers
    0.06
    Act Density 0.006%

    No Known Activations