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

    Neuronpedia

    INDEX
    Explanations

    exceptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .ident
    -0.08
     rezerv
    -0.08
    edef
    -0.08
     –↵
    -0.08
     <<↵
    -0.08
     Temperature
    -0.08
    igneur
    -0.07
     reserved
    -0.07
     transports
    -0.07
     Reserve
    -0.07
    POSITIVE LOGITS
     역시
    0.10
     przypadku
    0.09
     ఇద
    0.09
     همین
    0.09
     ámbito
    0.09
     kunjalo
    0.09
     విష
    0.08
     बाब
    0.08
     cazul
    0.08
     частности
    0.08
    Act Density 0.037%

    No Known Activations