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

    Neuronpedia

    INDEX
    Explanations

    way

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Payment
    -0.07
    相较
    -0.07
     trợ
    -0.07
     Braun
    -0.06
     הקר
    -0.06
     practition
    -0.06
    옯
    -0.06
    绗
    -0.06
    .wp
    -0.06
    obsolete
    -0.06
    POSITIVE LOGITS
    gems
    0.07
    masters
    0.07
    移民
    0.07
    身子
    0.07
    _sm
    0.07
     HISTORY
    0.07
    粒
    0.07
     filings
    0.07
    议论
    0.07
     -*-
    0.07
    Act Density 0.024%

    No Known Activations