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

    Neuronpedia

    INDEX
    Explanations

    code dealing with numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    産
    -0.07
     Pyramid
    -0.06
    Wave
    -0.06
    Mad
    -0.06
    indle
    -0.06
     sponge
    -0.06
     Boot
    -0.06
    仔
    -0.06
    ryo
    -0.06
     поход
    -0.06
    POSITIVE LOGITS
     req
    0.07
    서울
    0.07
    .ease
    0.07
     профес
    0.06
    _rgb
    0.06
     works
    0.06
    .Email
    0.06
    .isnan
    0.06
    _until
    0.06
    eslint
    0.06
    Act Density 0.029%

    No Known Activations