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

    Neuronpedia

    INDEX
    Explanations

    programming constituents and components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     possui
    0.42
    wenn
    0.41
     सुद्धा
    0.41
    選擇
    0.40
     utilizes
    0.40
    ्यास
    0.39
    EOUS
    0.39
    哋
    0.38
     पण
    0.38
     では
    0.38
    POSITIVE LOGITS
     που
    0.56
     которые
    0.51
     относя
    0.49
     jotka
    0.49
    ujące
    0.49
     that
    0.48
     koje
    0.46
     שה
    0.46
     или
    0.45
     такие
    0.44
    Act Density 0.033%

    No Known Activations