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

    Neuronpedia

    INDEX
    Explanations

    instances of uncertainty or conditionality in statements

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

    at least in part

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddHtmlAttribute
    -0.34
     Cool
    -0.30
    ParseTree
    -0.29
    檔
    -0.29
     Bright
    -0.29
     Warm
    -0.28
     extension
    -0.28
     Lightboxes
    -0.28
     ldc
    -0.28
     gate
    -0.28
    POSITIVE LOGITS
    :✨
    0.65
    Personendaten
    0.57
    hånd
    0.55
    Datuak
    0.54
     AssemblyCulture
    0.51
    RenderAtEndOf
    0.51
    bootstrapcdn
    0.50
    Gambas
    0.50
     فريبيس
    0.49
    GraphicsUnit
    0.49
    Act Density 0.060%

    No Known Activations