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

    Neuronpedia

    INDEX
    Explanations

    including inclusive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     为了
    0.52
     一个
    0.51
    了一個
    0.49
     我们
    0.48
    了一种
    0.47
     每个
    0.46
     করেছিল
    0.46
    {$\
    0.45
    袭
    0.45
     计算
    0.44
    POSITIVE LOGITS
     inclusiv
    0.49
    including
    0.48
     inclusive
    0.47
    inclusive
    0.45
    Including
    0.45
     रिच
    0.44
     Inclusive
    0.44
     inclus
    0.44
     empowers
    0.44
     sits
    0.43
    Act Density 0.011%

    No Known Activations