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

    Neuronpedia

    INDEX
    Explanations

    technical forum questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    契机
    -0.07
    ’.↵↵
    -0.07
    öße
    -0.07
    uncan
    -0.06
    鐘
    -0.06
    捆绑
    -0.06
     Jessica
    -0.06
     alleges
    -0.06
    下来的
    -0.06
    _Position
    -0.06
    POSITIVE LOGITS
    (U
    0.07
    mono
    0.07
     Tong
    0.07
     soy
    0.07
     graves
    0.07
    DOT
    0.07
     postal
    0.07
    _ctx
    0.07
     unitOfWork
    0.07
     au
    0.06
    Act Density 0.124%

    No Known Activations