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

    Neuronpedia

    INDEX
    Explanations

    Math expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ystone
    -0.08
    stdexcept
    -0.08
    adow
    -0.08
    udeau
    -0.07
     attributeName
    -0.07
    ToPoint
    -0.07
    发达国家
    -0.07
    ilst
    -0.07
    稳步
    -0.07
    atisch
    -0.07
    POSITIVE LOGITS
    .Tool
    0.07
    اعة
    0.07
    _audio
    0.07
    )</
    0.07
    Rx
    0.07
    ()</
    0.07
    ;/
    0.07
    兮
    0.07
     Like
    0.07
    num
    0.07
    Act Density 0.072%

    No Known Activations