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

    Neuronpedia

    INDEX
    Explanations

    introductions and numbered lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    으로
    0.49
     takeaway
    0.49
     hạ
    0.49
    يش
    0.48
     arrears
    0.48
     sót
    0.47
     deduce
    0.47
     across
    0.46
     reactors
    0.46
     halal
    0.46
    POSITIVE LOGITS
    al
    0.66
    с
    0.62
    та
    0.61
    ak
    0.60
    el
    0.57
    <0xA0>
    0.55
    ene
    0.54
    itt
    0.53
    ोन
    0.53
    id
    0.52
    Act Density 0.023%

    No Known Activations