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

    Neuronpedia

    INDEX
    Explanations

    assets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    杰
    -0.07
     tấm
    -0.07
     Soros
    -0.07
     telev
    -0.06
    澳
    -0.06
    advisor
    -0.06
    _sink
    -0.06
     CMS
    -0.06
     天
    -0.06
     Bac
    -0.06
    POSITIVE LOGITS
    .tiles
    0.08
    :NSLayout
    0.07
     tq
    0.07
    perimental
    0.06
    	length
    0.06
    |)↵
    0.06
    BitFields
    0.06
     acts
    0.06
     Matrix
    0.06
     qualification
    0.06
    Act Density 0.052%

    No Known Activations