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

    Neuronpedia

    INDEX
    Explanations

    doctor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ємо
    0.71
    ف
    0.70
    Ком
    0.68
     rø
    0.66
    د
    0.62
     Ј
    0.61
     马
    0.61
     К
    0.61
     日
    0.61
    ༠
    0.61
    POSITIVE LOGITS
    ing
    0.88
    inthe
    0.85
    and
    0.81
    p
    0.79
    vents
    0.79
    that
    0.78
    imped
    0.75
    to
    0.75
    ills
    0.75
    ference
    0.74
    Act Density 0.032%

    No Known Activations