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

    Neuronpedia

    INDEX
    Explanations

    Indian states and cities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Но
    0.71
    Си
    0.69
    мери
    0.68
     Matcha
    0.68
    Ди
    0.67
     Sankt
    0.66
    Ма
    0.66
     Kür
    0.65
    아
    0.65
    Э
    0.65
    POSITIVE LOGITS
    وں
    0.73
    Delhi
    0.71
     দিল্লির
    0.68
    Punjab
    0.68
     الهند
    0.66
     ର
    0.65
    Indian
    0.64
     delhi
    0.64
    arrivée
    0.64
     दिल्ली
    0.63
    Act Density 0.030%

    No Known Activations