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

    Neuronpedia

    INDEX
    Explanations

    data types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ب
    2.98
    in
    2.14
    ম
    1.99
    서
    1.95
    بك
    1.91
    ল
    1.73
    م
    1.73
    து
    1.72
    ব
    1.71
    بق
    1.70
    POSITIVE LOGITS
     Recogn
    1.59
    窕
    1.51
    >)
    1.47
     وبين
    1.44
    ⏯
    1.42
    ଐ
    1.41
     fera
    1.39
    薫
    1.34
     unor
    1.34
    িক্ষে
    1.34
    Act Density 0.071%

    No Known Activations