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

    Neuronpedia

    INDEX
    Explanations

    Russian and Eastern European contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inequities
    0.48
    цију
    0.47
    畴
    0.47
    滢
    0.46
    纽约
    0.46
     statunitense
    0.46
    ције
    0.46
    Maryland
    0.46
    绅
    0.45
     américaine
    0.45
    POSITIVE LOGITS
     Soviet
    1.48
     Volga
    1.41
     Moscow
    1.39
     Belarusian
    1.39
     Russian
    1.38
     Novosibirsk
    1.34
     Kyiv
    1.31
    Soviet
    1.29
     Kremlin
    1.28
     Leningrad
    1.27
    Act Density 0.033%

    No Known Activations