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

    Neuronpedia

    INDEX
    Explanations

    Travel itineraries

    np_max-act · gemini-2.0-flash

    The neuron picks out proper place names (cities and sites) in travel‐plan text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ID
    -0.08
    _slice
    -0.06
     copper
    -0.06
    -room
    -0.06
    _ap
    -0.06
    LEG
    -0.06
     Fiber
    -0.06
    olta
    -0.06
    uty
    -0.06
    Road
    -0.06
    POSITIVE LOGITS
     той
    0.07
    できます
    0.06
    ällt
    0.06
    (frames
    0.06
     جنوب
    0.06
     swal
    0.06
    جم
    0.06
     нельзя
    0.06
     фил
    0.06
     кот
    0.06
    Act Density 0.019%

    No Known Activations