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

    Neuronpedia

    INDEX
    Explanations

    attachment

    np_max-act · gemini-2.0-flash

    This neuron responds to technical action words (verbs describing processes or operations) in the patent text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    uni
    -0.07
    我
    -0.07
     foliage
    -0.07
    $f
    -0.07
    xes
    -0.07
    しています
    -0.06
     finalist
    -0.06
     reachable
    -0.06
    ople
    -0.06
    Aside
    -0.06
    POSITIVE LOGITS
    Rest
    0.06
     khai
    0.06
     gulp
    0.06
     MAG
    0.06
    …..
    0.06
     Kır
    0.06
     взаим
    0.06
    ฤษ
    0.06
     Programm
    0.06
     electrónico
    0.05
    Act Density 0.071%

    No Known Activations