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

    Neuronpedia

    INDEX
    Explanations

    references to scientific publications or citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    journal volume numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wikimedijinoj
    -0.57
    multer
    -0.52
    }{*}{}
    -0.52
    PyExc
    -0.50
    AddAttribute
    -0.49
     "];
    -0.46
    ]";
    -0.46
    Manbalar
    -0.45
    */
    -0.45
     */
    -0.44
    POSITIVE LOGITS
    期刊论文
    0.65
     deepening
    0.38
    новниш
    0.38
     Италијани
    0.35
    はじめに
    0.35
    RTSN
    0.34
     greu
    0.34
    0.33
    ThemeOverlay
    0.33
    yntaxException
    0.33
    Act Density 0.124%

    No Known Activations