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

    Neuronpedia

    INDEX
    Explanations

    code implementation-related terms and classes

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

    Code implementation names

    np_acts-logits-general · gemini-2.0-flash

    Impl implementation classes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lenker
    -0.60
    inSlope
    -0.55
    WireFormatLite
    -0.50
    transQ
    -0.49
    ValueStyle
    -0.45
    horesis
    -0.43
    RegressionTest
    -0.42
     présidentielle
    -0.41
     Aza
    -0.40
     Matta
    -0.40
    POSITIVE LOGITS
    impl
    0.66
    ServiceImpl
    0.63
    IMPL
    0.62
    Impl
    0.56
     impl
    0.56
    DaoImpl
    0.52
    DAOImpl
    0.47
     مواليد
    0.44
    ypeł
    0.44
     deleteById
    0.42
    Act Density 0.152%

    No Known Activations