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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating copyright and authorship in documents

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

    Code or formatting punctuation

    np_acts-logits-general · gemini-2.0-flash

    slash or comma followed by one

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.93
    UrlResolution
    -0.82
    parsedMessage
    -0.79
    InitVars
    -0.76
     للاسماء
    -0.76
    IsContent
    -0.74
     المعيارى
    -0.69
     оригіналу
    -0.69
    Архівовано
    -0.67
    SourceChecksum
    -0.67
    POSITIVE LOGITS
     stressed
    0.37
     sit
    0.34
    Project
    0.34
     Project
    0.33
     o
    0.32
     administrativos
    0.31
     student
    0.31
    highlighted
    0.31
     buruk
    0.30
    初
    0.30
    Act Density 0.034%

    No Known Activations