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

    Neuronpedia

    INDEX
    Explanations

    protect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     מ
    -0.07
    펑
    -0.07
     unitOfWork
    -0.07
     evolutionary
    -0.07
    يدي
    -0.07
     است
    -0.07
     ]).
    -0.07
     Tmin
    -0.06
    -hide
    -0.06
     Shi
    -0.06
    POSITIVE LOGITS
     arrangement
    0.08
    .concurrent
    0.08
     النساء
    0.07
     הקשור
    0.07
    农历
    0.07
    .balance
    0.07
    istorical
    0.07
    *K
    0.07
    .Formatting
    0.07
    相连
    0.07
    Act Density 0.088%

    No Known Activations