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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and phrases

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

    API operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BagConstraints
    -0.51
    XmlAccessorType
    -0.51
    BagLayout
    -0.49
    RunWith
    -0.46
     GlobalKey
    -0.46
    createClass
    -0.46
    tagHelper
    -0.45
     Wikimedijinoj
    -0.44
    (!__
    -0.43
    endsection
    -0.43
    POSITIVE LOGITS
    antası
    0.46
    はじめに
    0.46
     autorytatywna
    0.46
    0.44
    }{*}{}
    0.43
    ACHUSET
    0.42
     Roskov
    0.42
     purpoſe
    0.40
    leſs
    0.39
    Veuillez
    0.39
    Act Density 0.015%

    No Known Activations