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

    Neuronpedia

    INDEX
    Explanations

    case-sensitive punctuations and specific symbols in sentences

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

    dates and code identifiers

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

    numeric tokens and digit sequences in the text.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     väli
    -0.46
    XmlAccessType
    -0.45
     kyse
    -0.45
     pitä
    -0.42
     näytte
    -0.42
     hyö
    -0.42
     būs
    -0.40
     ģ
    -0.40
     käytt
    -0.40
     käyt
    -0.40
    POSITIVE LOGITS
    0.60
    KommentareTeilen
    0.55
     SqlCommand
    0.53
    endphp
    0.53
    Życiorys
    0.51
     referrerpolicy
    0.47
    withOpacity
    0.47
    GOTREF
    0.47
    PreInfinity
    0.47
     ModelExpression
    0.45
    Act Density 1.405%

    No Known Activations