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

    Neuronpedia

    INDEX
    Explanations

    punctuation and sentence endings

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

    dialogue or speech markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     złotych
    -0.39
    Dichloroethene
    -0.39
     toalha
    -0.38
     toalla
    -0.38
     planète
    -0.36
    hilangan
    -0.35
    ieteur
    -0.34
     rodada
    -0.34
     ")[
    -0.34
    ="/">
    -0.33
    POSITIVE LOGITS
     mergeFrom
    0.54
     désolés
    0.52
    Referències
    0.50
     ModelExpression
    0.48
    帖最后由
    0.47
    getSystemService
    0.47
     "..\..\..\
    0.47
    逅
    0.47
    XmlEnum
    0.47
    المكان
    0.46
    Act Density 0.014%

    No Known Activations