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

    Neuronpedia

    INDEX
    Explanations

    baking

    np_max-act · gemini-2.0-flash

    This neuron activates on baking or oven‐related cooking instructions, especially terms like “bake,” “baking,” and temperature references.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -tank
    -0.07
    (Current
    -0.06
     Filters
    -0.06
    astes
    -0.06
     bánh
    -0.06
    proved
    -0.06
    metadata
    -0.06
    γου
    -0.06
    (cap
    -0.06
     wom
    -0.06
    POSITIVE LOGITS
     è
    0.07
     playwright
    0.07
     questionable
    0.06
     keycode
    0.06
    	FILE
    0.06
    	gtk
    0.06
    SPACE
    0.06
     nghị
    0.06
     impover
    0.06
    廳
    0.06
    Act Density 0.008%

    No Known Activations