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

    Neuronpedia

    INDEX
    Explanations

    key terms related to scientific studies and their results

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

    quantities and descriptors

    np_acts-logits-general · gemini-2.5-flash-lite

    tokens that signal factual statements or methodological/results-related assertions in scientific/technical writing.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    adas
    -0.36
    vertical
    -0.34
    ad
    -0.34
    div
    -0.32
     Imp
    -0.32
    Ad
    -0.32
    Div
    -0.31
     Ad
    -0.31
    last
    -0.31
     Tor
    -0.31
    POSITIVE LOGITS
     disambiguazione
    0.82
    fromnode
    0.73
    rungsseite
    0.72
     itſelf
    0.69
    참고
    0.68
     tartalomajánló
    0.65
     Monfieur
    0.65
    ंदीखरीदारी
    0.63
    exitRule
    0.62
     raiſ
    0.62
    Act Density 0.368%

    No Known Activations