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

    Neuronpedia

    INDEX
    Explanations

    code structure and object-oriented programming elements, especially class definitions and inheritance

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

    Class inheritance ("extends")

    np_acts-logits-general · gemini-2.0-flash

    class inheritance (extends)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ParallelGroup
    -0.56
    adpleegd
    -0.54
    ImageContext
    -0.51
    awtextra
    -0.51
     оригіналу
    -0.50
     disambiguazione
    -0.50
    WriteBarrier
    -0.50
     ModelExpression
    -0.48
    IntoConstraints
    -0.48
    RotationOrder
    -0.48
    POSITIVE LOGITS
     base
    1.13
    Base
    1.12
     Base
    1.09
    Abstract
    1.02
    base
    0.98
     Abstract
    0.97
    abstract
    0.96
     abstract
    0.95
     bases
    0.85
    BaseEntity
    0.84
    Act Density 0.360%

    No Known Activations