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

    Neuronpedia

    INDEX
    Explanations

    geographic coordinates

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens naming geospatial data fields—especially precise location coordinates (e.g. “coordinates,” “latitude,” “longitude,” “elevation”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ipient
    -0.06
    IMENT
    -0.06
    Ticks
    -0.06
    лод
    -0.06
    Username
    -0.06
     chóng
    -0.06
     oro
    -0.06
    618
    -0.06
    -notification
    -0.05
    edula
    -0.05
    POSITIVE LOGITS
    ných
    0.08
     Sea
    0.08
    (User
    0.07
    ,q
    0.07
    =args
    0.07
    .states
    0.07
     assay
    0.07
     sext
    0.07
     Panel
    0.06
     Strateg
    0.06
    Act Density 0.018%

    No Known Activations