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

    Neuronpedia

    INDEX
    Explanations

    Arabic words and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    大法
    0.98
     بندی
    0.95
    ٬
    0.94
    𝚏
    0.92
    ﹐
    0.90
     गर्नुहोस्
    0.90
    𝙛
    0.90
     وکړئ
    0.89
    setFixedHeight
    0.89
    债
    0.88
    POSITIVE LOGITS
    <bos>
    1.05
    ළ
    1.00
    nh
    0.98
     Vire
    0.95
    ्ह
    0.93
    atsiooni
    0.87
     scipy
    0.87
     나서
    0.85
    ты
    0.85
     Islam
    0.85
    Act Density 0.006%

    No Known Activations