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

    Neuronpedia

    INDEX
    Explanations

    numeric values in a structured format, possibly related to certain identifiers or data points

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

    foreign languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     onCancelled
    -0.41
    kmäler
    -0.38
     Canary
    -0.35
    NewRow
    -0.35
     Pingback
    -0.35
     null
    -0.34
     Ore
    -0.33
    goed
    -0.33
    ph
    -0.33
     always
    -0.33
    POSITIVE LOGITS
     disponibilités
    0.70
     '\\;'
    0.63
    EndContext
    0.58
     okuyayım
    0.58
     تضيفلها
    0.54
    曖昧さ回避
    0.52
     Italijanski
    0.51
    libft
    0.51
     ujednoznacz
    0.50
     näh
    0.49
    Act Density 0.071%

    No Known Activations