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

    Neuronpedia

    INDEX
    Explanations

    class func

    np_max-act · gemini-2.0-flash

    object-oriented source code constructs, especially class and member declarations with access/type keywords.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
     attract
    -0.07
     شخص
    -0.06
    ły
    -0.06
    ;k
    -0.06
     edu
    -0.06
    ง
    -0.06
    _images
    -0.06
    .getHeader
    -0.06
     Roy
    -0.06
     کاربر
    -0.06
    POSITIVE LOGITS
     соци
    0.06
     HC
    0.06
    isphere
    0.06
    غة
    0.06
    icí
    0.06
    ukt
    0.06
    ith
    0.06
    ITH
    0.06
    Cog
    0.06
     соці
    0.06
    Act Density 0.067%

    No Known Activations