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

    Neuronpedia

    INDEX
    Explanations

    Widget

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    util
    0.51
     util
    0.46
     фа
    0.45
     bells
    0.44
    assembling
    0.43
     ContentValues
    0.41
    Util
    0.40
     utilisons
    0.40
     fas
    0.40
     베
    0.40
    POSITIVE LOGITS
    Widget
    0.80
     Widget
    0.75
     Widgets
    0.75
     widget
    0.72
     widgets
    0.67
    Widgets
    0.64
    widget
    0.63
    widgets
    0.54
     Wig
    0.49
     wig
    0.43
    Act Density 0.003%

    No Known Activations