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

    Neuronpedia

    INDEX
    Explanations

    location, navigation

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of being “in” a location or state (e.g. “in a room,” “in a safe space,” “where you are”) to track user location/safety context.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     endurance
    -0.07
     PLAN
    -0.06
    ocese
    -0.06
    .actions
    -0.06
    .goal
    -0.06
     LIGHT
    -0.06
     custody
    -0.06
     propagated
    -0.06
    Sunday
    -0.06
    -chain
    -0.06
    POSITIVE LOGITS
    ’app
    0.08
     Yardım
    0.07
     junto
    0.06
     Plains
    0.06
     olduğ
    0.06
    -awaited
    0.06
    'app
    0.06
    坐在
    0.06
     fontWithName
    0.06
    .setTextSize
    0.06
    Act Density 0.037%

    No Known Activations