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

    Neuronpedia

    INDEX
    Explanations

    all

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    有两种
    0.50
    Both
    0.48
     beiden
    0.45
     kedua
    0.44
     দুজনের
    0.40
     Both
    0.39
     Kedua
    0.38
     consisting
    0.38
     beide
    0.38
    毕竟
    0.37
    POSITIVE LOGITS
     كلها
    1.55
     সবই
    1.54
     allemaal
    1.52
     모두
    1.47
     semuanya
    1.47
    すべて
    1.38
     전부
    1.34
    这一切
    1.32
     tất
    1.30
     all
    1.27
    Act Density 0.026%

    No Known Activations