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

    Neuronpedia

    INDEX
    Explanations

    statements of corporate values beginning with "We"

    oai_token-act-pair · gemini-2.0-flash

    disclaimers/jargon

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ingtones
    -0.53
     Privacidade
    -0.47
    cenzo
    -0.47
    InstrumentedTest
    -0.47
    CELLANEOUS
    -0.46
    Життєпис
    -0.46
     utafitiHapana
    -0.46
    ணி
    -0.45
    endcsname
    -0.45
     阅读
    -0.42
    POSITIVE LOGITS
    はじめに
    0.67
     Paglinawan
    0.63
    TagHelpers
    0.62
    __(/*!
    0.62
    <bos>
    0.61
    clearInterval
    0.60
    كويكب
    0.59
    цезда
    0.58
     whereas
    0.54
    setof
    0.53
    Act Density 2.991%

    No Known Activations