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

    Neuronpedia

    INDEX
    Explanations

    distributions and licenses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ʢ
    0.30
    𝟭
    0.30
    Exceptions
    0.29
    给了
    0.29
    Bài
    0.28
    exécution
    0.28
    Đ
    0.28
    ji
    0.28
    Ს
    0.28
    ıyor
    0.27
    POSITIVE LOGITS
     earthen
    0.32
    に進
    0.32
     மொத்த
    0.29
     reproductions
    0.29
     sows
    0.29
    おそらく
    0.29
     redwood
    0.29
     linemen
    0.28
     legno
    0.28
     deoxy
    0.28
    Act Density 0.000%

    No Known Activations