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

    Neuronpedia

    INDEX
    Explanations

    code and technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    regnum
    -0.07
    Won
    -0.06
    shares
    -0.06
     нек
    -0.06
    interpre
    -0.06
     aun
    -0.06
    .tmp
    -0.06
     دون
    -0.06
    _tiles
    -0.06
     موب
    -0.06
    POSITIVE LOGITS
    .
↵
    0.07
    ์ได
    0.07
    >}↵
    0.06
    ").↵
    0.06
    ."+
    0.06
     **/↵↵
    0.06
    Elf
    0.06
    ".↵
    0.06
    니아
    0.06
    (regex
    0.06
    Act Density 0.000%

    No Known Activations