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

    Neuronpedia

    INDEX
    Explanations

    lottery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Từ
    1.06
     西
    1.03
     НА
    1.01
    ați
    0.99
     وعلى
    0.97
    Õ
    0.96
     Clínica
    0.96
     Chỉ
    0.96
    rocyte
    0.95
     đoạn
    0.94
    POSITIVE LOGITS
    as
    1.23
    z
    1.18
    ८
    1.13
    ne
    1.11
    im
    1.10
     migliori
    1.08
    ab
    1.07
    atz
    1.07
    j
    1.07
    π
    1.05
    Act Density 0.003%

    No Known Activations