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

    Neuronpedia

    INDEX
    Explanations

    references to class declarations in programming code

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

    java class usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.75
    -0.68
     Италијани
    -0.66
     المعيارى
    -0.61
    findpost
    -0.60
    fromnode
    -0.58
    Aholisi
    -0.57
    adaptiveStyles
    -0.57
    tangentMode
    -0.57
    setViewportView
    -0.56
    POSITIVE LOGITS
     class
    0.59
    class
    0.52
    msgTypes
    0.46
     getClass
    0.46
    ClassNotFound
    0.46
     Class
    0.46
    getClass
    0.42
     sizeof
    0.42
    ThroughAttribute
    0.42
    래스
    0.42
    Act Density 0.009%

    No Known Activations