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

    Neuronpedia

    INDEX
    Explanations

    viewing details or more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     befind
    0.80
     lies
    0.79
     lie
    0.75
    Ind
    0.67
     prestar
    0.66
     lying
    0.65
     sitt
    0.65
    ಃ
    0.65
     give
    0.64
    -[
    0.63
    POSITIVE LOGITS
    更多
    1.27
     more
    1.27
    更多的
    1.25
     altri
    1.24
     More
    1.21
     другие
    1.20
    其他
    1.18
     المزيد
    1.17
    more
    1.17
     другими
    1.14
    Act Density 0.001%

    No Known Activations