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

    Neuronpedia

    INDEX
    Explanations

    preposition: in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ंकि
    0.80
    šanas
    0.78
    ására
    0.72
    క్క
    0.71
    ത്തേ
    0.70
     whereof
    0.69
    ത്തേക്ക്
    0.67
     siitä
    0.67
    ֡
    0.66
    棻
    0.65
    POSITIVE LOGITS
     trong
    4.24
     in
    4.16
    ใน
    4.10
     dalam
    4.04
     في
    3.78
     în
    3.73
     katika
    3.27
     в
    3.09
    ໃນ
    3.07
    dalam
    3.07
    Act Density 1.994%

    No Known Activations