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

    Neuronpedia

    INDEX
    Explanations

    the presence of special tokens that may signal the beginning or end of sections or entries in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    numerical data or statistical information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    following results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.78
    itudinal
    -0.71
    MIDDLEWARE
    -0.70
    HtmlAttribute
    -0.66
     mapStateToProps
    -0.66
    المناصب
    -0.65
     بيها
    -0.64
    Bioaccumulative
    -0.60
    InvalidProtocol
    -0.60
    XmlAccessorType
    -0.60
    POSITIVE LOGITS
    regler
    0.52
     kenyataan
    0.50
     mivel
    0.46
    Background
    0.45
    <sup>
    0.44
     skolan
    0.43
     bakgrund
    0.43
     Parr
    0.43
     mensuales
    0.42
     riservata
    0.42
    Act Density 0.049%

    No Known Activations