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

    Neuronpedia

    INDEX
    Explanations

    country

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of “country” (i.e. when the user requests or labels the geographic location by country).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     přep
    -0.06
    Reality
    -0.06
     peaks
    -0.06
    _CON
    -0.06
    でき
    -0.06
     nostra
    -0.06
    _tiles
    -0.06
     beaucoup
    -0.06
    .scrollTop
    -0.06
     initializes
    -0.06
    POSITIVE LOGITS
     taxed
    0.07
     dwelling
    0.07
     Kenny
    0.07
     less
    0.06
     finans
    0.06
     dresser
    0.06
     justifyContent
    0.06
    ублі
    0.06
    /am
    0.06
     flown
    0.06
    Act Density 0.001%

    No Known Activations