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

    Neuronpedia

    INDEX
    Explanations

    locations/places in different languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dietary
    0.41
    It
    0.41
     pursuant
    0.40
     concurrency
    0.39
     arrhyth
    0.38
     uptime
    0.38
     datasource
    0.38
     protobuf
    0.38
     affected
    0.37
     verbal
    0.37
    POSITIVE LOGITS
     호텔
    0.57
    机场
    0.55
     restaurantes
    0.54
    超市
    0.54
     supermarket
    0.52
     মসজিদে
    0.52
     restoran
    0.52
    餐厅
    0.51
    レストラン
    0.50
     airport
    0.49
    Act Density 0.052%

    No Known Activations