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

    Neuronpedia

    INDEX
    Explanations

    recent years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bạn
    0.73
     doesn
    0.70
     dijeron
    0.69
    如果你
    0.63
    you
    0.60
     wasn
    0.59
     didn
    0.59
     你
    0.59
     você
    0.57
     don
    0.56
    POSITIVE LOGITS
    近年
    0.80
     Challenges
    0.71
    Besides
    0.70
    近年来
    0.70
    除了
    0.68
    Recent
    0.67
     characterized
    0.67
    Challenges
    0.65
     Recent
    0.64
     характеризу
    0.64
    Act Density 0.005%

    No Known Activations