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

    Neuronpedia

    INDEX
    Explanations

    initials and/or names of people and companies

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.68
    出版年
    -0.62
    +#+#
    -0.47
     means
    -0.43
    reen
    -0.42
    __["
    -0.42
     mean
    -0.42
     who
    -0.41
    Provincia
    -0.41
    ruth
    -0.40
    POSITIVE LOGITS
    Pautan
    0.62
    ynchronously
    0.60
    __':
    0.58
     externi
    0.58
    thenReturn
    0.57
    ticides
    0.56
    Identyfik
    0.54
     Roskov
    0.53
    boutin
    0.52
    Ucraina
    0.52
    Act Density 0.249%

    No Known Activations