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

    Neuronpedia

    INDEX
    Explanations

    **

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itur
    -0.08
     quae
    -0.08
    quia
    -0.07
    -growing
    -0.07
    Jesu
    -0.07
    fq
    -0.07
    <P
    -0.07
     fq
    -0.07
     troops
    -0.07
    ālā
    -0.07
    POSITIVE LOGITS
     NOTE
    0.09
     লক্ষ্য
    0.09
    IMPORTANT
    0.08
     লক্ষ
    0.08
     গুরুত্ব
    0.08
     важно
    0.08
     আইন
    0.08
     Buckingham
    0.08
     reconsider
    0.08
    Warning
    0.08
    Act Density 0.012%

    No Known Activations