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

    Neuronpedia

    INDEX
    Explanations

    terms related to programming structures and object attributes

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

    Code snippets with variables

    np_acts-logits-general · gemini-2.0-flash

    programming identifiers and assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TypedDataSet
    -0.72
     Roskov
    -0.67
     propOrder
    -0.64
    oa̍t
    -0.63
    usercontent
    -0.62
    DeleteBehavior
    -0.61
     autorytatywna
    -0.57
    LookAnd
    -0.56
    UnsafeEnabled
    -0.56
    uxxxx
    -0.55
    POSITIVE LOGITS
     is
    0.43
    ver
    0.42
    《
    0.40
    pura
    0.39
     main
    0.38
    main
    0.38
    package
    0.38
     kun
    0.38
     won
    0.38
    DAS
    0.37
    Act Density 0.585%

    No Known Activations