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

    Neuronpedia

    INDEX
    Explanations

    references to constructed narratives or meta-narrative elements within texts

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

    breaking the fourth wall

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.65
     protoimpl
    -0.53
    keyColumn
    -0.50
    ymce
    -0.50
    SharedDtor
    -0.48
    createCell
    -0.48
    tagHelperRunner
    -0.46
    ViewFeatures
    -0.46
     ExecuteAsync
    -0.46
    iastes
    -0.45
    POSITIVE LOGITS
     autorytatywna
    0.46
    bkz
    0.45
    ⓧ
    0.40
     okuyayım
    0.39
    riebene
    0.38
     rocas
    0.36
    SourceChecksum
    0.36
    WindowConstants
    0.36
     Nachfolger
    0.36
     discí
    0.35
    Act Density 0.203%

    No Known Activations