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

    Neuronpedia

    INDEX
    Explanations

    the term 'lang' within file paths

    oai_token-act-pair · gemini-2.0-flash

    lang

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -1.54
     the
    -0.60
     you
    -0.53
    '
    -0.51
    وزيع
    -0.50
     their
    -0.46
    sendStatus
    -0.45
    ゴリー
    -0.45
    updateUI
    -0.44
     updates
    -0.44
    POSITIVE LOGITS
    enterOuterAlt
    0.72
    Datuak
    0.71
     فريبيس
    0.71
    setVerticalGroup
    0.69
     Pingback
    0.68
    esModule
    0.68
    TagMode
    0.67
     JAXB
    0.62
     оригіналу
    0.61
    存于互联网档案馆
    0.60
    Act Density 0.133%

    No Known Activations