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

    Neuronpedia

    INDEX
    Explanations

    academic or scholarly references and citations

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

    Punctuation immediately following a word

    np_acts-logits-general · gemini-2.0-flash

    symbols and separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ddelwed
    -0.68
     المعيارى
    -0.65
     queſta
    -0.63
     wikipagina
    -0.61
    Życiorys
    -0.60
    tanleria
    -0.60
    ſſung
    -0.60
     パンチラ
    -0.60
    expandindo
    -0.60
     Geſch
    -0.58
    POSITIVE LOGITS
    ↵↵
    0.51
    :
    0.48
     +
    0.44
     vs
    0.44
    ↵
    0.44
    @
    0.43
     =
    0.42
     /
    0.41
     &
    0.40
     
    0.40
    Act Density 1.553%

    No Known Activations