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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    oai_token-act-pair · gemini-2.0-flash

    Code/Foreign Languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    出版年
    -0.90
    riwal
    -0.75
     myſelf
    -0.73
    protoimpl
    -0.72
    ngdoc
    -0.71
    uxxxx
    -0.70
     Normdatei
    -0.69
    ⓧ
    -0.69
    ſelf
    -0.69
    yntaxException
    -0.66
    POSITIVE LOGITS
     no
    0.41
     extinción
    0.37
     plais
    0.37
     str
    0.37
     teh
    0.36
    ként
    0.36
     appréci
    0.34
     singoli
    0.33
     Вікіпе
    0.33
     esprits
    0.33
    Act Density 0.101%

    No Known Activations