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

    Neuronpedia

    INDEX
    Explanations

    historical states and dynasties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tunisia
    0.88
     Malawi
    0.85
     Zambia
    0.85
     Botswana
    0.85
     Bangalore
    0.84
     Namibia
    0.84
     Calabria
    0.82
     Maroc
    0.82
     dubai
    0.81
     Burundi
    0.79
    POSITIVE LOGITS
     People
    0.73
    People
    0.66
     Greater
    0.65
    Greater
    0.60
    Autonomous
    0.60
     Peoples
    0.59
     Autonomous
    0.54
    Democratic
    0.54
     পুর্ব
    0.51
     पूर्व
    0.51
    Act Density 0.295%

    No Known Activations