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

    Neuronpedia

    INDEX
    Explanations

    Olympic athletes and events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ي
    0.76
    s
    0.70
    es
    0.64
    ل
    0.62
    r
    0.58
    er
    0.56
    下に
    0.55
    ς
    0.55
    y
    0.55
    unica
    0.54
    POSITIVE LOGITS
    IN
    0.64
     to
    0.59
     olymp
    0.56
     by
    0.54
    .
    0.50
     zeggen
    0.49
     we
    0.47
    IS
    0.46
     Processor
    0.45
     you
    0.45
    Act Density 0.001%

    No Known Activations