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

    Neuronpedia

    INDEX
    Explanations

    negative auxiliary verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     באמצעות
    1.00
     एवं
    0.86
     אשר
    0.85
    此外
    0.84
     amelyet
    0.81
     посредством
    0.77
     الذي
    0.76
    Thus
    0.76
     számos
    0.76
    更に
    0.76
    POSITIVE LOGITS
     isn
    1.87
     didn
    1.80
     wasn
    1.78
     doesn
    1.77
     aren
    1.76
     shouldn
    1.72
     wouldn
    1.67
     weren
    1.62
     hasn
    1.60
     hadn
    1.56
    Act Density 0.268%

    No Known Activations