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

    Neuronpedia

    INDEX
    Explanations

    specific references to groups, categories, or classifications in a structured context

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

    (E) followed by number or parenthesis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الحره
    -0.75
    AndEndTag
    -0.68
    сылкі
    -0.63
    出版年
    -0.62
     المعيارى
    -0.61
    gameserver
    -0.61
    RTEX
    -0.61
    RenderAtEndOf
    -0.60
     Administrativna
    -0.60
     disambiguazione
    -0.59
    POSITIVE LOGITS
    5
    0.61
     fifth
    0.60
     Fifth
    0.54
     quinto
    0.50
    fifth
    0.48
    4
    0.48
     D
    0.46
     quinta
    0.46
    第五
    0.45
     пя
    0.45
    Act Density 0.308%

    No Known Activations