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

    Neuronpedia

    INDEX
    Explanations

    Prime Minister or loop samples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Surface
    -0.07
     buddies
    -0.07
     attendee
    -0.07
     seaw
    -0.06
     bothers
    -0.06
     synchronization
    -0.06
     AV
    -0.06
    iy
    -0.06
     welcomed
    -0.06
    easy
    -0.06
    POSITIVE LOGITS
     celui
    0.07
    (always
    0.07
    Use
    0.06
    /use
    0.06
    ्द
    0.06
    ══
    0.06
    ον
    0.06
    shire
    0.06
     "");
↵
    0.06
     bụ
    0.06
    Act Density 0.006%

    No Known Activations