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

    Neuronpedia

    INDEX
    Explanations

    Eastern Europe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ীর
    0.90
    T
    0.75
    Т
    0.75
     N
    0.73
    ﺲ
    0.72
    A
    0.70
    lie
    0.70
    v
    0.69
    kę
    0.68
    5
    0.68
    POSITIVE LOGITS
    ik
    0.82
     Countries
    0.79
     Balkans
    0.77
    ੋ
    0.75
     Hungarian
    0.69
     Polska
    0.68
     Pologne
    0.68
     Bulgarian
    0.67
     दिलों
    0.67
    ap
    0.66
    Act Density 0.006%

    No Known Activations