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

    Neuronpedia

    INDEX
    Explanations

    "meal" or "meals"

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of “meal” (including “Meal” or “meals”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     white
    -0.07
     conspir
    -0.07
     Copper
    -0.07
    qtt
    -0.07
     Tiger
    -0.07
     Outline
    -0.07
    ाहक
    -0.07
     činnosti
    -0.07
     Focus
    -0.07
     Feder
    -0.06
    POSITIVE LOGITS
     meal
    0.11
     Meal
    0.11
    Meal
    0.09
     meals
    0.08
    meal
    0.07
     Meals
    0.07
     medal
    0.07
     Coleman
    0.07
    ELL
    0.07
    al
    0.07
    Act Density 0.004%

    No Known Activations