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

    Neuronpedia

    INDEX
    Explanations

    punctuations and symbols used in programming or coding contexts

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

    code syntax delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.75
    ⟬
    -0.69
     snippetHide
    -0.63
    әрмәләр
    -0.58
    <unused41>
    -0.57
    <unused28>
    -0.57
    <unused52>
    -0.57
    <unused68>
    -0.57
    <pad>
    -0.57
    <unused23>
    -0.57
    POSITIVE LOGITS
     CanadaChoose
    0.33
    GetAsync
    0.33
     aperçu
    0.30
    RTEE
    0.30
     الأ
    0.29
     uğ
    0.28
     acompaña
    0.27
     división
    0.27
    งาม
    0.27
     ympä
    0.27
    Act Density 0.382%

    No Known Activations