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

    Neuronpedia

    INDEX
    Explanations

    real-time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vezes
    0.78
    raz
    0.78
    Related
    0.78
     следует
    0.77
     `>=`,
    0.77
    اتها
    0.76
    с
    0.76
     meses
    0.76
    此之外
    0.76
    咒
    0.75
    POSITIVE LOGITS
     estate
    2.23
    istically
    2.05
    politik
    1.98
     ESTATE
    1.79
     Estate
    1.78
    ignment
    1.73
    estate
    1.71
    Estate
    1.67
    igning
    1.62
    igned
    1.60
    Act Density 0.077%

    No Known Activations