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

    Neuronpedia

    INDEX
    Explanations

    foreign languages and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    A
    0.75
    n
    0.70
    p
    0.59
    J
    0.58
     ford
    0.53
    gdf
    0.53
    N
    0.53
    r
    0.50
    X
    0.49
    T
    0.49
    POSITIVE LOGITS
     څرنګ
    0.57
     Гуляць
    0.56
     chromos
    0.54
     Кан
    0.53
    언
    0.53
     Стаўкі
    0.53
    ವಿದೆ
    0.52
    の値
    0.52
     какво
    0.50
     sandwiched
    0.49
    Act Density 0.000%

    No Known Activations