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

    Neuronpedia

    INDEX
    Explanations

    markers indicating generated content or auto-generated sections

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

    code comments and headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -1.35
    parsedMessage
    -1.25
     Meksiku
    -1.20
    RenderAtEndOf
    -1.19
    GraphicsUnit
    -1.17
    <unused41>
    -1.15
    <unused51>
    -1.15
    <unused17>
    -1.15
    <unused8>
    -1.15
    <unused14>
    -1.15
    POSITIVE LOGITS
    ↵↵
    0.45
    ↵
    0.41
    1
    0.39
      
    0.36
    import
    0.35
    2
    0.34
    .
    0.34
    ↵↵↵
    0.34
    <blockquote>
    0.34
    ↵↵↵↵
    0.33
    Act Density 0.015%

    No Known Activations