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

    Neuronpedia

    INDEX
    Explanations

    then

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Peggy
    -0.06
    Por
    -0.06
    ../../../
    -0.06
     ig
    -0.06
     capitals
    -0.06
    734
    -0.06
    boxes
    -0.06
     sais
    -0.06
     багать
    -0.06
    سمة
    -0.06
    POSITIVE LOGITS
    然后
    0.08
     then
    0.07
    0.07
    0.07
     Uploaded
    0.07
    CallBack
    0.07
    +b
    0.07
     ++↵
    0.07
     ثم
    0.07
     sonrasında
    0.07
    Act Density 0.023%

    No Known Activations