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

    Neuronpedia

    INDEX
    Explanations

    text formatting elements and structural tags

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

    HTML links and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.79
     CreateTagHelper
    -0.77
     nakalista
    -0.76
    SourceChecksum
    -0.75
     defaultstate
    -0.73
     noDo
    -0.72
    -0.68
     ModelExpression
    -0.65
    pushFollow
    -0.65
     Paglinawan
    -0.65
    POSITIVE LOGITS
     music
    0.40
    s
    0.35
    jumu
    0.34
    NodeId
    0.33
     staff
    0.32
     urgent
    0.32
     música
    0.32
    <i>
    0.32
    literal
    0.31
     chair
    0.31
    Act Density 0.000%

    No Known Activations