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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and symbols used in formatting or coding contexts

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

    digital, reponse, box, post, was, bath

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    errHandler
    -0.52
    }{*}{
    -0.52
     فريبيس
    -0.50
    يميديا
    -0.48
     ModelExpression
    -0.47
     ویکی‌پدیا
    -0.47
     незавершена
    -0.46
    Архівовано
    -0.46
    دانشنامهٔ
    -0.45
    httphttps
    -0.45
    POSITIVE LOGITS
     <<=
    0.48
     >>
    0.47
     >>>
    0.46
    medriver
    0.45
     Photocase
    0.43
     >>=
    0.42
     >
    0.42
    >>
    0.41
     contextLoads
    0.41
     purpoſe
    0.40
    Act Density 0.066%

    No Known Activations