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

    Neuronpedia

    INDEX
    Explanations

    code-related commands and their properties

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

    "default" or variations of it

    np_acts-logits-general · gemini-2.0-flash

    by default

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -0.80
     protoimpl
    -0.69
    ImageContext
    -0.66
    اریخ
    -0.62
    EndGlobalSection
    -0.62
    QMetaType
    -0.62
     ModelExpression
    -0.61
    tagHelperRunner
    -0.61
    GEBURTSDATUM
    -0.60
     cherchés
    -0.60
    POSITIVE LOGITS
     default
    3.52
    default
    3.21
     Default
    2.82
    Default
    2.75
     defaults
    2.46
    默认
    2.35
     DEFAULT
    2.27
    DEFAULT
    2.23
     defaulted
    2.22
    デフォ
    2.06
    Act Density 0.225%

    No Known Activations