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

    Neuronpedia

    INDEX
    Explanations

    activity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    出し
    -0.08
     muster
    -0.07
    ꒳
    -0.07
     False
    -0.07
     ella
    -0.07
     repost
    -0.07
    둁
    -0.07
    幡
    -0.07
     yeti
    -0.07
     preach
    -0.07
    POSITIVE LOGITS
    广场
    0.08
    Sites
    0.08
    .Images
    0.08
    eneration
    0.07
    环氧
    0.07
    公安局
    0.07
    Steven
    0.07
     sites
    0.07
    涉足
    0.07
    /////
    0.06
    Act Density 0.009%

    No Known Activations