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

    Neuronpedia

    INDEX
    Explanations

    either/or choices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    يات
    1.21
     CPUs
    1.21
    ט
    1.20
    y
    1.10
    りに
    1.09
     ATMs
    1.08
    יה
    1.06
    ларга
    1.06
     सुद्धा
    1.05
    सुद्धा
    1.05
    POSITIVE LOGITS
    Either
    1.10
    ли
    1.07
    もしくは
    1.06
     หรือ
    1.02
    或
    1.02
    {~
    0.94
     or
    0.92
     atau
    0.92
    ня
    0.91
     либо
    0.91
    Act Density 0.019%

    No Known Activations