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

    Neuronpedia

    INDEX
    Explanations

    japanese patent publications

    np_max-act · gemini-2.0-flash

    The neuron detects patent publication numbers (numeric codes with hyphens) in technical documents.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Lic
    -0.07
    berry
    -0.07
    Demo
    -0.07
     mej
    -0.06
     zaměstn
    -0.06
    jun
    -0.06
    Fil
    -0.06
     老
    -0.06
    刀
    -0.06
    ress
    -0.06
    POSITIVE LOGITS
     paint
    0.06
     можно
    0.06
    upos
    0.06
    ')),
    0.06
     abnormal
    0.06
    [state
    0.06
     munch
    0.06
    ASIC
    0.06
     chasing
    0.06
    	Transform
    0.06
    Act Density 0.002%

    No Known Activations