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

    Neuronpedia

    INDEX
    Explanations

    parts of or aspects of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    σεων
    0.55
     donations
    0.52
    进来
    0.50
     এখানে
    0.49
     तिथे
    0.49
     زیبا
    0.49
    さんは
    0.48
    それを
    0.47
     როგორ
    0.47
     последний
    0.47
    POSITIVE LOGITS
     của
    2.11
    ของ
    1.89
     of
    1.88
     của
    1.84
     של
    1.74
     ofthe
    1.63
    ຂອງ
    1.52
     της
    1.45
    នៃ
    1.45
    របស់
    1.41
    Act Density 0.323%

    No Known Activations