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

    Neuronpedia

    INDEX
    Explanations

    references to collaborative research and different types of publications

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

    Academic publications and citations

    np_acts-logits-general · gemini-2.0-flash

    academic paper components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AttributeSet
    -0.61
    windowFixed
    -0.59
    رامج
    -0.56
     Efq
    -0.55
    mbg
    -0.54
     surla
    -0.54
    mtrl
    -0.54
     Prophe
    -0.54
    kmale
    -0.54
    ENOMEM
    -0.53
    POSITIVE LOGITS
     journal
    1.18
     journals
    1.04
     publication
    1.01
     paper
    1.00
     Journal
    0.97
     papers
    0.95
     peer
    0.93
     abstract
    0.89
     publishing
    0.88
     citation
    0.88
    Act Density 2.242%

    No Known Activations