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

    Neuronpedia

    INDEX
    Explanations

    multimedia and multimodal concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    C
    1.02
    1
    0.97
    S
    0.91
    中国
    0.90
    Q
    0.87
    N
    0.86
    此
    0.86
    kart
    0.83
    kosť
    0.83
    这个
    0.82
    POSITIVE LOGITS
    ש
    1.05
    ین
    0.93
    ত
    0.88
    ле
    0.84
    ною
    0.82
     yattha
    0.82
    ので
    0.81
     زیرا
    0.80
     zemlji
    0.80
    ্ব
    0.79
    Act Density 0.019%

    No Known Activations