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

    Neuronpedia

    INDEX
    Explanations

    toe nailing and short cycling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]+=
    0.43
     prez
    0.41
    riter
    0.41
    iters
    0.38
    溃
    0.38
     Bishops
    0.38
    jects
    0.37
    ப்ர
    0.37
    endous
    0.37
     étages
    0.37
    POSITIVE LOGITS
     trùng
    0.40
     ফু
    0.38
     bang
    0.36
     multival
    0.36
    Tại
    0.35
     fare
    0.35
    ringer
    0.34
    云计算
    0.34
     фу
    0.34
     পল্ল
    0.34
    Act Density 0.000%

    No Known Activations