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

    Neuronpedia

    INDEX
    Explanations

    references to widgets in a graphical user interface context

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

    UI widgets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unlucky
    -0.36
    )}+\
    -0.36
    *)&
    -0.36
    *}\
    -0.35
    begin
    -0.35
    --){
    -0.35
    })+\
    -0.34
    }`}
    -0.34
    ]=-
    -0.34
    không
    -0.34
    POSITIVE LOGITS
     widget
    1.75
     createState
    1.52
     Widget
    1.52
     widgets
    1.44
     Widgets
    1.34
    widget
    1.16
    Widget
    1.05
    WIDGET
    0.93
    widgets
    0.92
    Widgets
    0.85
    Act Density 0.001%

    No Known Activations