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

    Neuronpedia

    INDEX
    Explanations

    episode of tv series

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ння
    1.29
     can
    0.99
    زی
    0.94
    otonic
    0.92
     the
    0.87
    นี้
    0.84
    usian
    0.82
    ugia
    0.81
    voir
    0.80
    ется
    0.79
    POSITIVE LOGITS
     episode
    1.23
     épisode
    1.16
     episodios
    1.10
     episodes
    1.09
    Ди
    1.07
     histoire
    1.03
    ليك
    1.02
    إ
    1.02
    5
    1.00
    রা
    0.99
    Act Density 0.002%

    No Known Activations