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

    Neuronpedia

    INDEX
    Explanations

    references to code documentation or annotations

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

    code and links in documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OrWhiteSpace
    -0.44
     indígen
    -0.43
     <>",
    -0.42
     cruce
    -0.41
    endphp
    -0.41
     ouv
    -0.40
     للمعارف
    -0.40
     commandement
    -0.40
    ndose
    -0.39
     armé
    -0.39
    POSITIVE LOGITS
     {@
    1.29
    {@
    0.94
    }{@
    0.65
    >{@
    0.60
    OGND
    0.52
     }{@
    0.51
     nahilalakip
    0.50
     للاسماء
    0.50
     @{
    0.50
    inheritDoc
    0.49
    Act Density 0.002%

    No Known Activations