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

    Neuronpedia

    INDEX
    Explanations

    documents with no significant content or activations

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

    Follows a reserved word in code

    np_acts-logits-general · gemini-2.0-flash

    patterns preceding punctuation or specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PreferredItem
    -0.73
     esternos
    -0.69
    цездатний
    -0.63
    úgó
    -0.63
     Italijanski
    -0.57
    benhavn
    -0.56
    ArrowToggle
    -0.56
     multiuso
    -0.56
    agissait
    -0.54
     OFDb
    -0.53
    POSITIVE LOGITS
    TypedDataSet
    0.89
    DBNull
    0.65
    chaik
    0.60
     timeval
    0.57
     ligiloj
    0.53
    bitField
    0.52
     lạnh
    0.51
    DataSet
    0.50
     >=",
    0.49
    istoitu
    0.48
    Act Density 0.013%

    No Known Activations