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

    Neuronpedia

    INDEX
    Explanations

    Bharat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ı
    1.35
    ა
    1.25
    et
    1.09
    i
    1.06
    ą
    1.06
    í
    1.05
    x
    1.02
    а
    0.93
     ожида
    0.93
    4
    0.92
    POSITIVE LOGITS
    س
    1.05
    驩
    0.99
    ने
    0.99
    al
    0.96
    لى
    0.95
     می‌تواند
    0.92
     quaternion
    0.89
    醤
    0.88
    ль
    0.88
    वर्ष
    0.88
    Act Density 0.003%

    No Known Activations