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

    Neuronpedia

    INDEX
    Explanations

    questions and uncertainty regarding data or claims

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

    asking questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    featureID
    -0.48
     bArr
    -0.42
     <<<<<<<<<<<<<<
    -0.42
    UseVisualStyle
    -0.42
    AnchorTagHelper
    -0.40
     Roles
    -0.39
    GraphicsUnit
    -0.39
    queryInterface
    -0.39
    ContentAsync
    -0.38
     hikariConfig
    -0.38
    POSITIVE LOGITS
     بيها
    0.53
    rungsseite
    0.53
     surla
    0.44
    Tikang
    0.40
    UnsafeEnabled
    0.39
    cifix
    0.39
    قرير
    0.39
     cycle
    0.38
     Anfrage
    0.38
    preduce
    0.37
    Act Density 0.104%

    No Known Activations