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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of local administrative units—terms like parish, civil parish, manor, hundred, etc.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     undecided
    -0.07
     نمی
    -0.07
    翔
    -0.06
    	Create
    -0.06
    wię
    -0.06
     Fake
    -0.06
     نق
    -0.06
    Crypt
    -0.06
    ecided
    -0.06
    pcl
    -0.06
    POSITIVE LOGITS
     agriculture
    0.08
    roducing
    0.07
    _increase
    0.07
    imesteps
    0.07
    ilities
    0.06
    package
    0.06
    IRO
    0.06
    rotation
    0.06
    6
    0.06
     denne
    0.06
    Act Density 0.009%

    No Known Activations