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

    Neuronpedia

    INDEX
    Explanations

    user's geographical location

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     qīng
    0.42
     faiblement
    0.40
     terlibat
    0.39
     maž
    0.38
     Longer
    0.37
    WithDictionary
    0.37
    粧
    0.36
     samband
    0.36
     найден
    0.35
    риса
    0.35
    POSITIVE LOGITS
     geographical
    0.86
     geographic
    0.84
     California
    0.73
     Canada
    0.73
     géographique
    0.73
     region
    0.72
     geograf
    0.72
     US
    0.68
     USA
    0.68
     Netherlands
    0.68
    Act Density 0.158%

    No Known Activations