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

    Neuronpedia

    INDEX
    Explanations

    The

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     the
    0.85
     dunno
    0.73
    了一些
    0.72
    ayu
    0.66
     our
    0.65
     effectually
    0.64
    OTE
    0.62
     impatiently
    0.62
    *,
    0.61
    *
    0.60
    POSITIVE LOGITS
     Dissertation
    0.93
     Deuteronomy
    0.93
     Legal
    0.93
     Curso
    0.92
     Decreto
    0.90
     Rounds
    0.89
     Dispute
    0.89
     ምልክ
    0.88
     Цвет
    0.88
    grades
    0.88
    Act Density 0.015%

    No Known Activations