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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .toList
    -0.07
    stands
    -0.07
    наруж
    -0.07
    _putstr
    -0.07
    (Expression
    -0.07
     ************************************************
    -0.07
     RGB
    -0.07
     *));↵
    -0.06
    .copyOf
    -0.06
    ("",
    -0.06
    POSITIVE LOGITS
     Vintage
    0.06
    experiment
    0.06
    束
    0.06
    سن
    0.06
    require
    0.06
    謝
    0.06
    eced
    0.06
     Bảo
    0.06
     Riverside
    0.06
    URRE
    0.06
    Act Density 0.011%

    No Known Activations