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

    Neuronpedia

    INDEX
    Explanations

    Dairy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ди
    1.01
    し
    0.95
    لي
    0.92
    ה
    0.88
    ного
    0.82
    يرا
    0.80
    த்து
    0.79
    น
    0.79
    ږئ
    0.77
    يث
    0.76
    POSITIVE LOGITS
    ak
    1.27
    ik
    0.95
     Dairy
    0.93
    ana
    0.89
    p
    0.84
     dairy
    0.83
    的产品
    0.82
    ain
    0.81
    Dairy
    0.76
    ien
    0.76
    Act Density 0.002%

    No Known Activations