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

    Neuronpedia

    INDEX
    Explanations

    key-value pair structures in code related to text fields

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

    content descriptions and labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.90
    migrationBuilder
    -0.80
    SharedCtor
    -0.79
    IsMutable
    -0.77
    featureID
    -0.76
     CreateTagHelper
    -0.74
     &___
    -0.73
    addCriterion
    -0.72
     مرئيه
    -0.71
    astéroïdes
    -0.71
    POSITIVE LOGITS
     content
    0.34
    jScrollPane
    0.34
    内容
    0.32
     فض
    0.31
    JScrollPane
    0.30
    HTML
    0.29
     description
    0.29
    Scri
    0.29
     bie
    0.28
    Sk
    0.28
    Act Density 0.007%

    No Known Activations