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

    Neuronpedia

    INDEX
    Explanations

    cities

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     چیز
    0.52
     sovi
    0.51
    roquois
    0.50
     পূর্ববাংলার
    0.50
     সোভিয়েত
    0.49
     Thoreau
    0.49
     소련
    0.49
    嵇
    0.49
     soviet
    0.48
     believable
    0.47
    POSITIVE LOGITS
     London
    0.80
     Barcelona
    0.72
     Paris
    0.69
     Beijing
    0.69
     Istanbul
    0.68
     Bengaluru
    0.68
     Dubai
    0.67
     Mumbai
    0.67
     Amsterdam
    0.66
    London
    0.66
    Act Density 0.022%

    No Known Activations