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

    Neuronpedia

    INDEX
    Explanations

    itineraries

    np_max-act · gemini-2.0-flash

    This neuron detects itinerary‐style step markers—tokens like “Day,” day numbers, bullet symbols, and the imperative verbs that introduce each travel plan step.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     rehabilit
    -0.07
    dek
    -0.07
    bond
    -0.06
    -js
    -0.06
     Auburn
    -0.06
     Button
    -0.06
    notation
    -0.06
    oran
    -0.06
     Heal
    -0.06
    (TR
    -0.06
    POSITIVE LOGITS
     Nom
    0.07
     ISS
    0.06
     VAT
    0.06
     massively
    0.06
    ريق
    0.06
     nominees
    0.06
     niveau
    0.06
     prenatal
    0.06
     провод
    0.06
    등록
    0.06
    Act Density 0.034%

    No Known Activations