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

    Neuronpedia

    INDEX
    Explanations

    references to external and internal contexts or spaces

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

    outside or external

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.61
    aarrggbb
    -0.59
     nakalista
    -0.58
    Cyfarwyddwr
    -0.56
    richTextPanel
    -0.55
    الدراسه
    -0.53
    RTEE
    -0.53
     ویکی‌پدیا
    -0.50
     disponibilités
    -0.50
     المعيارى
    -0.50
    POSITIVE LOGITS
    Outside
    1.17
     Outside
    1.16
     inside
    1.15
     exterior
    1.13
     outside
    1.13
    inside
    1.13
    Inside
    1.12
    outside
    1.11
    exterior
    1.09
     OUTSIDE
    1.09
    Act Density 0.216%

    No Known Activations