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

    Neuronpedia

    INDEX
    Explanations

    say

    np_max-act · gemini-2.0-flash

    This neuron activates on metalinguistic “when we say that…” or similar phrasing that signals a definition or explanation is about to follow.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    okrat
    -0.07
    "Do
    -0.06
    _crit
    -0.06
     genotype
    -0.06
     Recycling
    -0.06
    cio
    -0.06
     히
    -0.06
    foods
    -0.06
     SE
    -0.06
     Personality
    -0.06
    POSITIVE LOGITS
     Erica
    0.06
     Aux
    0.06
     Xã
    0.06
    External
    0.06
     toast
    0.06
     produkt
    0.06
    тю
    0.06
     Olympia
    0.06
    breadcrumb
    0.06
    igner
    0.06
    Act Density 0.029%

    No Known Activations