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

    Neuronpedia

    INDEX
    Explanations

    light concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    或是
    0.74
    もしくは
    0.66
    或
    0.66
     interdependent
    0.66
     hoặc
    0.65
     или
    0.63
     insanların
    0.63
     또는
    0.62
    或者是
    0.61
     లేదా
    0.61
    POSITIVE LOGITS
     glory
    0.63
     glories
    0.62
    inescence
    0.61
    ใช้
    0.60
     woes
    0.60
     ગયા
    0.57
     сча
    0.56
    也不
    0.56
    を使う
    0.55
     antics
    0.55
    Act Density 0.000%

    No Known Activations