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

    Neuronpedia

    INDEX
    Explanations

    contrast

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (),
↵
    -0.07
    ami
    -0.06
     �
    -0.06
    issant
    -0.06
    _decoder
    -0.06
    ())
    -0.06
    ’
    -0.06
     encodeURIComponent
    -0.06
    _loc
    -0.06
    '
    -0.06
    POSITIVE LOGITS
    hap
    0.07
     पत
    0.06
     doubled
    0.06
    .archive
    0.06
     goat
    0.06
     holy
    0.06
     infos
    0.06
    Soap
    0.06
     gifs
    0.06
     аль
    0.06
    Act Density 0.058%

    No Known Activations