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

    Neuronpedia

    INDEX
    Explanations

    Roman Empire

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sultan
    0.97
     शेख
    0.83
     archipelago
    0.83
     Freezer
    0.82
     mango
    0.82
     Aw
    0.80
     Singers
    0.80
     sultan
    0.79
     Sharif
    0.79
    ズニー
    0.79
    POSITIVE LOGITS
     рим
    1.80
     Roman
    1.56
     Romans
    1.50
     रोमन
    1.41
    Roman
    1.38
     romanos
    1.35
     Rome
    1.35
     Рим
    1.32
     Hadrian
    1.29
    Romans
    1.26
    Act Density 0.165%

    No Known Activations