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

    Neuronpedia

    INDEX
    Explanations

    refers to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ໄລ
    0.77
    必备
    0.70
     अधिकारी
    0.69
     শরণ
    0.68
     holidays
    0.68
     ssize
    0.68
     चौहान
    0.68
     hotels
    0.67
    ໃນ
    0.67
     הי
    0.66
    POSITIVE LOGITS
    keit
    0.77
    aligned
    0.74
    keras
    0.74
    mechan
    0.73
    времен
    0.73
     nieder
    0.72
    schrift
    0.71
    sche
    0.71
     wenige
    0.71
     keresztül
    0.71
    Act Density 0.012%

    No Known Activations