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

    Neuronpedia

    INDEX
    Explanations

    numbers and arithmetic operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ninety
    0.99
     Ninety
    0.99
     九
    0.95
     Ninth
    0.94
    ９
    0.89
     September
    0.88
     ۹
    0.87
     nineteen
    0.86
    九
    0.85
     ৯
    0.85
    POSITIVE LOGITS
     four
    1.59
    4
    1.55
     Four
    1.48
    Four
    1.47
    four
    1.43
     நான்கு
    1.36
    FOUR
    1.36
     четыре
    1.36
     चार
    1.33
     നാല
    1.32
    Act Density 0.327%

    No Known Activations