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

    Neuronpedia

    INDEX
    Explanations

    user interface toolkits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    喝
    0.50
     کمر
    0.40
    喝酒
    0.40
    drinking
    0.40
    bacteria
    0.39
    סטר
    0.39
     drinking
    0.39
    ジャン
    0.39
    ="/">
    0.38
     ಸೇವ
    0.38
    POSITIVE LOGITS
     UI
    1.23
     widgets
    1.18
     widget
    1.14
     Widgets
    1.14
     Widget
    1.13
     Layout
    1.13
     GUI
    1.09
    UI
    1.03
    Widget
    1.03
    Widgets
    1.03
    Act Density 0.020%

    No Known Activations