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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate knowledge or established facts

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

    known facts or common knowledge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.90
     estekak
    -0.54
    XmlAccessorType
    -0.54
    MessageTagHelper
    -0.50
    ContentAsync
    -0.50
    ագրություններ
    -0.49
     Photocase
    -0.48
     ویکی‌پدی
    -0.47
     ModelExpression
    -0.47
     Roskov
    -0.47
    POSITIVE LOGITS
     known
    0.59
     bekan
    0.54
     know
    0.54
    known
    0.54
     Known
    0.52
     conocidas
    0.51
    know
    0.50
    Known
    0.49
    要知道
    0.48
    我知道
    0.47
    Act Density 0.187%

    No Known Activations