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

    Neuronpedia

    INDEX
    Explanations

    command line arguments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ዝ
    -0.07
    码
    -0.07
    TEX
    -0.07
     growing
    -0.07
     Would
    -0.07
     COL
    -0.06
    估值
    -0.06
    Ve
    -0.06
     auctions
    -0.06
     stitch
    -0.06
    POSITIVE LOGITS
    第二次
    0.07
     pleasures
    0.07
     הבע
    0.07
     advers
    0.07
     cerebral
    0.07
    앍
    0.06
     logfile
    0.06
    行政审批
    0.06
    .adapter
    0.06
     לצפ
    0.06
    Act Density 0.012%

    No Known Activations