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

    Neuronpedia

    INDEX
    Explanations

    registry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (off
    -0.08
    汔
    -0.07
    热销
    -0.07
     :]↵
    -0.07
     ensuring
    -0.07
     quat
    -0.07
    ᵐ
    -0.06
     UCHAR
    -0.06
    ↵↵
    -0.06
    貨
    -0.06
    POSITIVE LOGITS
     Elvis
    0.07
     בי
    0.07
     Atlantis
    0.07
     backers
    0.07
    틔
    0.07
    웝
    0.07
     Święt
    0.06
    ߎ
    0.06
    (STD
    0.06
    _SITE
    0.06
    Act Density 0.027%

    No Known Activations