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

    Neuronpedia

    INDEX
    Explanations

    references to functions in programming or software contexts

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

    functions that return

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pecabe
    -0.44
    StoreMessageInfo
    -0.43
    StatusBadRequest
    -0.42
     ModelExpression
    -0.42
    WriteBarrier
    -0.42
    AnimationsModule
    -0.41
    sendRedirect
    -0.40
     تضيفلها
    -0.40
     Anfitrión
    -0.40
     Monfieur
    -0.40
    POSITIVE LOGITS
     function
    0.62
     Function
    0.56
     method
    0.52
     함수
    0.52
    的方法
    0.51
     func
    0.50
    contentLoaded
    0.49
    func
    0.49
    Funciones
    0.49
     Functions
    0.48
    Act Density 0.035%

    No Known Activations