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

    Neuronpedia

    INDEX
    Explanations

    BBQ food and restaurants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     масштаб
    0.93
     ק
    0.92
     מ
    0.91
     με
    0.88
     მ
    0.87
     καθώς
    0.86
     το
    0.86
     საერთ
    0.85
     pozw
    0.84
    ों
    0.83
    POSITIVE LOGITS
    و
    1.21
    ا
    1.08
    ير
    1.03
    ری
    1.02
    ه
    1.01
    لي
    0.99
    نا
    0.98
    ed
    0.97
    ة
    0.97
    ா
    0.96
    Act Density 0.001%

    No Known Activations