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

    Neuronpedia

    INDEX
    Explanations

    ruler

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    详情
    -0.07
    .FILES
    -0.06
     тв
    -0.06
    \/\/
    -0.06
     tremend
    -0.06
    _CHARS
    -0.06
    짜
    -0.06
     симв
    -0.06
     LANGUAGE
    -0.06
    nestjs
    -0.06
    POSITIVE LOGITS
     ruler
    0.07
    .SO
    0.07
    Bạn
    0.07
    yz
    0.07
     Jama
    0.06
     Autonomous
    0.06
     поверхности
    0.06
     Reyes
    0.06
    shutdown
    0.06
    Dock
    0.06
    Act Density 0.001%

    No Known Activations