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

    Neuronpedia

    INDEX
    Explanations

    Legal proceedings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     works
    -0.06
    .ft
    -0.06
    lines
    -0.06
    罗斯
    -0.06
    会议
    -0.06
     turns
    -0.06
     Trailer
    -0.06
     Laurel
    -0.06
    돌
    -0.06
     Але
    -0.06
    POSITIVE LOGITS
     Sergio
    0.08
     collider
    0.06
     downside
    0.06
    urgical
    0.06
     McKin
    0.06
     Donald
    0.06
     Unsigned
    0.06
    556
    0.06
    >");↵↵
    0.06
     MULTI
    0.06
    Act Density 0.018%

    No Known Activations