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

    Neuronpedia

    INDEX
    Explanations

    online services/product descriptions

    np_max-act · gemini-2.0-flash

    The neuron fires on technical numerical references—numbers, units, version or standard identifiers, and other spec‐style tokens in product or protocol descriptions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Scripture
    -0.07
     seaborn
    -0.06
     insistence
    -0.06
     plate
    -0.06
    _assert
    -0.06
     June
    -0.06
     Verm
    -0.06
     particle
    -0.06
     pudding
    -0.06
    λία
    -0.06
    POSITIVE LOGITS
     espan
    0.07
     uzav
    0.07
    ází
    0.06
     Odkazy
    0.06
     Nich
    0.06
    fullName
    0.06
    исс
    0.06
     bliss
    0.06
     accord
    0.06
    0.06
    Act Density 0.189%

    No Known Activations