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

    Neuronpedia

    INDEX
    Explanations

    concepts related to programming structures such as classes and interfaces

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

    Code definitions: class, interface, struct, type, enum

    np_acts-logits-general · gemini-2.0-flash

    exported or public definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jLabel
    -0.81
     Method
    -0.66
    pyplot
    -0.64
    richTextPanel
    -0.63
    Method
    -0.59
    HasAnnotation
    -0.58
     FUNC
    -0.56
     METHOD
    -0.56
     Function
    -0.55
    getMenuInflater
    -0.55
    POSITIVE LOGITS
    class
    1.26
     class
    1.22
    interface
    0.84
    abstract
    0.83
     abstract
    0.80
     interface
    0.74
    enum
    0.73
    sealed
    0.71
     enum
    0.68
    struct
    0.64
    Act Density 0.113%

    No Known Activations