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

    Neuronpedia

    INDEX
    Explanations

    references to figures and graphs within the text

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

    figure, illustration, or abbreviation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DebuggerNonUser
    -0.48
     المعيارى
    -0.48
    Tembelea
    -0.45
    XmlAccessType
    -0.42
    getSelectedItem
    -0.42
    ulets
    -0.41
    liferay
    -0.41
    +#+
    -0.41
     subter
    -0.41
     мәкал
    -0.40
    POSITIVE LOGITS
     Figure
    0.78
     figure
    0.73
     Figures
    0.72
    Figure
    0.69
     figura
    0.68
    figure
    0.67
     figures
    0.67
     abbildung
    0.66
     Abbildung
    0.65
     Fig
    0.64
    Act Density 1.155%

    No Known Activations