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

    Neuronpedia

    INDEX
    Explanations

    patterns related to references and citations in academic texts

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

    authors' initials followed by names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     חיצוניים
    -0.55
    رشف
    -0.54
     للاسماء
    -0.53
    urlpatterns
    -0.52
     Wikimedijinoj
    -0.51
     history
    -0.48
     nors
    -0.48
    ReusableCell
    -0.47
     فريبيس
    -0.47
    History
    -0.46
    POSITIVE LOGITS
    MessageTagHelper
    0.75
    MigrationBuilder
    0.74
    ?,?,
    0.67
    transQ
    0.63
    sidemargin
    0.60
    Viitteet
    0.60
    #
    0.59
     تانيه
    0.59
     rentrée
    0.59
    ۜ
    0.59
    Act Density 0.038%

    No Known Activations