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

    Neuronpedia

    INDEX
    Explanations

    code snippets that define classes in object oriented programming languages

    oai_token-act-pair · gemini-2.0-flash

    programming code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    adaptiveStyles
    -0.46
    CppMethod
    -0.45
    gameserver
    -0.45
     Abar
    -0.42
     pinulongan
    -0.42
    ISupport
    -0.40
     ’
    -0.39
    ’.”
    -0.39
    ctively
    -0.39
    pdev
    -0.39
    POSITIVE LOGITS
     createdBy
    0.72
     getPrice
    0.70
    HasAnnotation
    0.70
     companyId
    0.70
     posX
    0.69
     getIndex
    0.68
    دانشنامهٔ
    0.67
     startDate
    0.67
     roomId
    0.67
     loadData
    0.65
    Act Density 7.623%

    No Known Activations