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

    Neuronpedia

    INDEX
    Explanations

    class definitions in code

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

    python class definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    VYMaps
    -0.62
    fromnode
    -0.48
     EconPapers
    -0.47
     ivelany
    -0.47
     sumpay
    -0.42
    stdafx
    -0.42
     atof
    -0.42
    WebElementEntity
    -0.42
    ArrowToggle
    -0.41
    URIComponent
    -0.41
    POSITIVE LOGITS
    class
    0.88
     class
    0.67
    Class
    0.63
     Class
    0.57
     clase
    0.52
    TagMode
    0.51
     klasy
    0.50
     клас
    0.49
    CLASS
    0.49
     sınıf
    0.47
    Act Density 0.001%

    No Known Activations