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

    Neuronpedia

    INDEX
    Explanations

    sudo

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     amort
    -0.07
     telefon
    -0.07
    ervice
    -0.07
     destroyer
    -0.07
     elektr
    -0.07
     radical
    -0.06
     industri
    -0.06
     hypers
    -0.06
    .Hour
    -0.06
     auch
    -0.06
    POSITIVE LOGITS
    sudo
    0.31
     sudo
    0.25
    udo
    0.11
    UDO
    0.08
    .slug
    0.07
     potato
    0.07
    误
    0.07
     Суд
    0.07
     Hero
    0.07
    صبح
    0.07
    Act Density 0.002%

    No Known Activations