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

    Neuronpedia

    INDEX
    Explanations

    widgets

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect occurrences of the word “widget.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Morse
    -0.08
    496
    -0.07
    -distance
    -0.07
    ore
    -0.07
     crossings
    -0.07
    eneral
    -0.07
    17
    -0.07
    18
    -0.07
    16
    -0.07
     över
    -0.06
    POSITIVE LOGITS
    	widget
    0.09
    Widget
    0.08
     Widget
    0.07
     Hayden
    0.07
     gadget
    0.07
    veled
    0.07
     widget
    0.07
    Featured
    0.07
    ода
    0.07
    ут
    0.07
    Act Density 0.005%

    No Known Activations