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

    Neuronpedia

    INDEX
    Explanations

    python print statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ቂያ
    0.94
    ángulos
    0.90
     către
    0.89
     توسط
    0.89
     إلى
    0.88
    ාව
    0.88
    stargo
    0.86
    Towards
    0.86
    gerät
    0.85
     بواسطة
    0.85
    POSITIVE LOGITS
    print
    1.33
     print
    1.13
     Print
    1.08
    Print
    0.95
     prints
    0.81
     Printing
    0.74
     Printed
    0.73
     PRINT
    0.72
    PRINT
    0.70
     An
    0.69
    Act Density 0.161%

    No Known Activations