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

    Neuronpedia

    INDEX
    Explanations

    zeroes and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Thirteen
    0.87
     Eleven
    0.86
     lima
    0.70
     शिवा
    0.68
    jima
    0.68
    OSPH
    0.68
    elje
    0.68
     ۲
    0.67
     Побе
    0.67
    १८४
    0.66
    POSITIVE LOGITS
    ००
    2.05
    ۰۰
    1.95
    ০০
    1.79
    ០០
    1.72
    0
    1.67
    oo
    1.61
     hundred
    1.55
    ၀၀
    1.46
    Hundred
    1.40
    OO
    1.40
    Act Density 1.216%

    No Known Activations