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

    Neuronpedia

    INDEX
    Explanations

    only followed by comma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    只需要
    0.42
    孃
    0.42
    朗普
    0.41
    ΤΟ
    0.41
    给
    0.40
    ╽
    0.40
    逮捕
    0.39
     صہیونیت
    0.39
    可以将
    0.38
     lateribus
    0.38
    POSITIVE LOGITS
     represents
    0.37
     Sans
    0.37
     seinen
    0.37
     Mereka
    0.36
     VK
    0.36
     verkrij
    0.36
     doesn
    0.36
    并不
    0.35
     approximately
    0.35
     Dabei
    0.35
    Act Density 0.003%

    No Known Activations