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

    Neuronpedia

    INDEX
    Explanations

    declarations and definitions of class methods and their properties in code

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

    Virtual class methods or function declarations

    np_acts-logits-general · gemini-2.0-flash

    public virtual methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    новниш
    -0.56
    BeginContext
    -0.53
    jspx
    -0.52
    Personendaten
    -0.52
    SpringBootTest
    -0.51
    nologue
    -0.49
    iane
    -0.49
     kaarangay
    -0.49
    bibitem
    -0.47
     Worth
    -0.46
    POSITIVE LOGITS
     methods
    1.23
    methods
    1.14
     Methods
    1.12
     method
    1.05
    Methods
    1.05
     métodos
    0.98
    method
    0.97
     METHODS
    0.93
     public
    0.93
     Method
    0.92
    Act Density 0.850%

    No Known Activations