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

    Neuronpedia

    INDEX
    Explanations

    toggle or switch states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InCM
    0.45
    ديد
    0.42
    scanf
    0.42
     анали
    0.41
     scanf
    0.40
    िद
    0.40
    磨
    0.40
    validacion
    0.39
    analyze
    0.39
     вакан
    0.39
    POSITIVE LOGITS
     Toggle
    0.97
     toggle
    0.96
    Toggle
    0.92
     togg
    0.87
    toggle
    0.81
    ToggleButton
    0.68
    切换
    0.61
     Switching
    0.59
     switching
    0.59
     Switch
    0.59
    Act Density 0.042%

    No Known Activations