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

    Neuronpedia

    INDEX
    Explanations

    division and fractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ư
    0.66
    3
    0.61
    år
    0.61
     परिणामस्वरूप
    0.59
    izamos
    0.59
    ран
    0.59
    ওয়ার
    0.58
    于
    0.58
    рани
    0.55
    ীক
    0.55
    POSITIVE LOGITS
     Half
    1.28
     half
    1.23
    Half
    1.07
    half
    1.04
     HALF
    0.94
    HALF
    0.94
     halfway
    0.93
     halves
    0.87
     cystic
    0.86
     halved
    0.84
    Act Density 0.167%

    No Known Activations