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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     evaluated
    -0.09
    |)↵
    -0.07
    这个行业
    -0.07
    _sig
    -0.07
    !)↵
    -0.07
     attached
    -0.07
    $__
    -0.07
    𬱟
    -0.07
    theast
    -0.07
    東
    -0.07
    POSITIVE LOGITS
     iOS
    0.07
     الآخر
    0.07
     hij
    0.07
    낯
    0.07
    aria
    0.07
    城墙
    0.06
    금융
    0.06
    urg
    0.06
     commenc
    0.06
    悄然
    0.06
    Act Density 0.001%

    No Known Activations