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

    Neuronpedia

    INDEX
    Explanations

    radio

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens naming or defining radio‐button controls (e.g. “radio,” “RadioButton,” group/name attributes), so it’s looking for radio‐button UI elements in the code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _TEMP
    -0.07
     ke
    -0.07
    .onDestroy
    -0.06
    	build
    -0.06
     Phill
    -0.06
    什么
    -0.06
     ni
    -0.06
     mi
    -0.06
    flowers
    -0.06
     اصفه
    -0.06
    POSITIVE LOGITS
    RadioButton
    0.07
    radio
    0.07
     MouseEvent
    0.07
     діє
    0.06
    ROY
    0.06
    cono
    0.06
    \ActiveForm
    0.06
    การ
    0.06
    adioButton
    0.06
    妖
    0.06
    Act Density 0.004%

    No Known Activations