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

    Neuronpedia

    INDEX
    Explanations

    calls to action regarding policies and community initiatives

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

    recommendations and proposed actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    msgTypes
    -0.58
    XmlAccessType
    -0.56
    styleType
    -0.55
     snippetHide
    -0.49
    UnsafeEnabled
    -0.47
    fxml
    -0.47
    routeProvider
    -0.45
    Халык
    -0.45
    ViewInit
    -0.42
    astify
    -0.41
    POSITIVE LOGITS
    maxAge
    0.36
    Ered
    0.35
     Elders
    0.34
    ///</
    0.33
    aryen
    0.33
    رشف
    0.33
    getUserId
    0.33
    说说
    0.33
    használ
    0.33
    nard
    0.32
    Act Density 0.284%

    No Known Activations