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

    Neuronpedia

    INDEX
    Explanations

    type/ref/event/out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -1.83
    絝
    -1.69
     dô
    -1.60
    mola
    -1.48
     ทำ
    -1.48
    蛱
    -1.45
    ſſen
    -1.41
    oved
    -1.41
    ೢ
    -1.41
    ᕮ
    -1.41
    POSITIVE LOGITS
     the
    1.92
    m
    1.62
    </h1>
    1.55
    dirkan
    1.46
     medica
    1.41
    bersicht
    1.38
     situa
    1.37
    ()<<
    1.33
    k
    1.32
     staten
    1.31
    Act Density 0.001%

    No Known Activations