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

    Neuronpedia

    INDEX
    Explanations

    sugar

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of “sugar” (especially when listed with amounts) in recipe text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     bas
    -0.07
     directing
    -0.06
    ньому
    -0.06
     panoramic
    -0.06
     viral
    -0.06
     boat
    -0.06
    .scan
    -0.06
     headache
    -0.06
    ibility
    -0.06
     characteristics
    -0.06
    POSITIVE LOGITS
    élé
    0.07
    отреб
    0.06
     maxSize
    0.06
     Candy
    0.06
     timeZone
    0.06
     UIScreen
    0.06
    (chalk
    0.06
    .Number
    0.06
    NoSuch
    0.06
    (Route
    0.06
    Act Density 0.003%

    No Known Activations