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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and structural symbols in the text

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

    <start_of_turn> user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     avoient
    -0.48
    เหร
    -0.48
    NameInMap
    -0.42
     enfans
    -0.41
    jeva
    -0.40
     nisso
    -0.38
    GNUC
    -0.37
     avoit
    -0.37
     Tanah
    -0.36
    Fordítás
    -0.36
    POSITIVE LOGITS
     disambiguazione
    0.58
    SourceChecksum
    0.55
     MessageBoxIcon
    0.54
    adpleegd
    0.52
    AnimationsModule
    0.48
    chartInstance
    0.47
    himovic
    0.47
     متعلقه
    0.46
    parsedMessage
    0.46
    Jeografia
    0.45
    Act Density 0.002%

    No Known Activations