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

    Neuronpedia

    INDEX
    Explanations

    phrases that express self-reflection or self-description

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

    start of user input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.78
    WritableDatabase
    -0.61
    WindowConstants
    -0.59
     للاسماء
    -0.59
     pinulongan
    -0.58
    parsedMessage
    -0.56
     المعيارى
    -0.55
     calendriers
    -0.54
    utilisons
    -0.54
    ########.
    -0.54
    POSITIVE LOGITS
     sich
    0.91
     zich
    0.55
    sich
    0.48
     się
    0.46
    endosi
    0.41
     se
    0.40
    andosi
    0.39
     itself
    0.38
     себе
    0.35
     Sich
    0.35
    Act Density 0.004%

    No Known Activations