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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Environment
    -0.07
     Flex
    -0.06
    +":
    -0.06
    aped
    -0.06
    uştur
    -0.06
    -green
    -0.06
     Jones
    -0.06
     Mé
    -0.06
    marked
    -0.06
     styles
    -0.06
    POSITIVE LOGITS
    　　 　 　
    0.07
    cido
    0.06
     flats
    0.06
    优秀
    0.06
     beneficiaries
    0.06
    _Q
    0.06
    /display
    0.06
    ليه
    0.06
    -gr
    0.06
    全国
    0.06
    Act Density 0.313%

    No Known Activations