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

    Neuronpedia

    INDEX
    Explanations

    code/math symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _tt
    -0.07
    imat
    -0.07
    chure
    -0.07
    adera
    -0.07
    _body
    -0.07
     Publishing
    -0.06
    .page
    -0.06
    Area
    -0.06
    开工建设
    -0.06
    仿
    -0.06
    POSITIVE LOGITS
    .birth
    0.07
     PYTHON
    0.07
     новый
    0.07
    stars
    0.07
    =fopen
    0.07
    Https
    0.07
    rule
    0.07
     oppos
    0.07
     Bread
    0.07
    linux
    0.06
    Act Density 0.064%

    No Known Activations