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

    Neuronpedia

    INDEX
    Explanations

    pyplot as, taste

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1.73
     walaupun
    1.13
     parecía
    1.11
    ہیں
    1.09
     nejen
    1.06
     esempio
    1.03
    하지만
    1.03
    ції
    1.02
     మీద
    1.02
    ส์
    1.02
    POSITIVE LOGITS
    ानंद
    1.10
     other
    1.09
    各类
    1.08
     अन्य
    0.94
    the
    0.92
    lable
    0.91
     सुभाष
    0.89
     마찬가지
    0.88
    l
    0.87
     অন্যান্য
    0.87
    Act Density 0.055%

    No Known Activations