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

    Neuronpedia

    INDEX
    Explanations

    code brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _subset
    -0.07
    Seen
    -0.07
     مرحله
    -0.06
    ネット
    -0.06
     Morton
    -0.06
    _lhs
    -0.06
     %#
    -0.06
    ":["
    -0.06
    тий
    -0.06
     quot
    -0.06
    POSITIVE LOGITS
     unpack
    0.06
    аш
    0.06
    linked
    0.06
     нап
    0.06
     налог
    0.06
     ABS
    0.06
    paging
    0.06
     bottoms
    0.06
     "_"
    0.06
     itu
    0.05
    Act Density 0.010%

    No Known Activations