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

    Neuronpedia

    INDEX
    Explanations

    Florence, Italy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    는
    0.99
    ی
    0.95
    них
    0.95
     घ्यावी
    0.94
    定め
    0.94
    ющих
    0.93
    {
    0.93
    니다
    0.92
    実施
    0.91
    是
    0.90
    POSITIVE LOGITS
     for
    1.15
     Firenze
    1.14
    C
    1.00
     be
    0.98
    p
    0.95
    ol
    0.94
    ку
    0.94
     Gothenburg
    0.93
    ac
    0.92
    M
    0.91
    Act Density 0.001%

    No Known Activations