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

    Neuronpedia

    INDEX
    Explanations

    questions starting with "What."

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

    "What" questions

    np_acts-logits-general · gemini-2.0-flash

    asking "what" questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     suivantes
    -0.72
    HtmlAttribute
    -0.72
    WriteTagHelper
    -0.69
    RectangleBorder
    -0.68
     BoxDecoration
    -0.66
    تقاوى
    -0.64
     ExecuteAsync
    -0.64
     suivants
    -0.62
    Tikang
    -0.62
    writeFieldEnd
    -0.62
    POSITIVE LOGITS
     kind
    1.06
     happens
    0.88
     else
    0.85
     type
    0.82
    kind
    0.81
     kinds
    0.81
     happened
    0.76
     sort
    0.76
     types
    0.75
     is
    0.74
    Act Density 0.149%

    No Known Activations