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

    Neuronpedia

    INDEX
    Explanations

    monetary values and ranges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     előtt
    0.23
     ৩৩
    0.22
     ২০১
    0.22
    挲
    0.22
    endus
    0.21
    aney
    0.21
    ৯
    0.21
     ৫১
    0.21
     millions
    0.21
    बे
    0.21
    POSITIVE LOGITS
     CAD
    0.32
    <unused1876>
    0.29
    фера
    0.29
    也许
    0.29
     Осо
    0.29
     Cũng
    0.29
     두
    0.28
     loafers
    0.28
     ಔಷಧ
    0.28
     useParams
    0.28
    Act Density 0.721%

    No Known Activations