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

    Neuronpedia

    INDEX
    Explanations

    occurrences of access modifiers in code, such as 'public' and 'private'

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

    Java or C# keywords ("static", "public", "boolean", "void")

    np_acts-logits-general · gemini-2.0-flash

    java method signatures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Clik
    -0.64
     المعيارى
    -0.54
    RenderAtEndOf
    -0.53
     rospy
    -0.53
     تضيفلها
    -0.46
     București
    -0.46
    Webpack
    -0.45
     Kaly
    -0.45
    IGraphics
    -0.45
    WriteTagHelper
    -0.43
    POSITIVE LOGITS
     void
    1.26
     boolean
    1.11
    void
    1.10
     bool
    0.97
    boolean
    0.93
    bool
    0.82
     int
    0.77
    IsContent
    0.71
     Boolean
    0.71
     {?>
    0.69
    Act Density 0.043%

    No Known Activations