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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash

    The neuron activates on geographic place names (cities, countries) when listing travel/location suggestions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Uncle
    -0.07
     GMT
    -0.06
    WEST
    -0.06
    -West
    -0.06
    Pet
    -0.06
    _dp
    -0.06
     wich
    -0.06
     donner
    -0.06
     Bound
    -0.06
    port
    -0.06
    POSITIVE LOGITS
    セット
    0.07
    sim
    0.07
    (images
    0.06
    LOCAL
    0.06
     medya
    0.06
     органів
    0.06
     beraber
    0.06
     витами
    0.06
    	None
    0.06
     الدولي
    0.06
    Act Density 0.084%

    No Known Activations