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

    Neuronpedia

    INDEX
    Explanations

    to get started

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     adds
    0.42
     theres
    0.40
     alternatives
    0.38
     explores
    0.38
    थी
    0.38
     penyebab
    0.38
    adds
    0.38
     encontraron
    0.37
     fanden
    0.37
     causas
    0.37
    POSITIVE LOGITS
    我会
    0.83
    给我
    0.79
    让我
    0.75
    給我
    0.74
    আমাকে
    0.72
     درخواست
    0.71
    讓我
    0.71
     요청
    0.70
    طيني
    0.68
    我已经
    0.68
    Act Density 0.243%

    No Known Activations