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

    Neuronpedia

    INDEX
    Explanations

    Patent country codes

    np_max-act · gemini-2.0-flash

    The neuron activates on patent publication identifiers, i.e. country codes plus document numbers (e.g. “US 2008/…,” “DE 10…,” “EP …”) indicating patent references.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    its
    -0.07
    .navigation
    -0.07
     evalu
    -0.06
    ......
    -0.06
    ีข
    -0.06
    .getItem
    -0.06
     omp
    -0.06
     Marr
    -0.06
    .Free
    -0.06
     병
    -0.06
    POSITIVE LOGITS
     desperate
    0.07
    jun
    0.06
    らない
    0.06
    owej
    0.06
    nid
    0.06
    艺
    0.06
     Princeton
    0.06
     kní
    0.06
     concentrates
    0.06
    .reactivex
    0.06
    Act Density 0.011%

    No Known Activations