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

    Neuronpedia

    INDEX
    Explanations

    news articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    secutive
    -0.07
    byss
    -0.07
    芙
    -0.06
     Observer
    -0.06
    ека
    -0.06
    Bru
    -0.06
    arme
    -0.06
     LAW
    -0.06
    琴
    -0.06
     Rück
    -0.06
    POSITIVE LOGITS
     Perform
    0.07
    /aws
    0.06
    .Site
    0.06
     ↵
    0.06
     sweeping
    0.06
    [".
    0.06
     nanop
    0.06
    _TOGGLE
    0.06
    .createClass
    0.06
     нее
    0.06
    Act Density 0.069%

    No Known Activations