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

    Neuronpedia

    INDEX
    Explanations

    sequences of underscores that may indicate formatting or placeholders in code

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

    programming code constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -1.16
    :✨
    -1.12
    NameInMap
    -1.09
    RenderAtEndOf
    -1.09
     disambiguazione
    -1.00
     EconPapers
    -0.97
     ujednoznacz
    -0.96
    delwed
    -0.93
     informée
    -0.93
    +#+#
    -0.90
    POSITIVE LOGITS
    if
    0.41
     if
    0.31
    for
    0.30
    //
    0.28
    8
    0.28
    1
    0.28
      
    0.27
    (
    0.26
     it
    0.26
    assemblée
    0.25
    Act Density 0.041%

    No Known Activations