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

    Neuronpedia

    INDEX
    Explanations

    out

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (',')[
    -0.07
    ბ
    -0.07
     OPP
    -0.07
    _REL
    -0.07
     ''){↵
    -0.07
    美丽的
    -0.06
    บ
    -0.06
    Gre
    -0.06
    地狱
    -0.06
    merc
    -0.06
    POSITIVE LOGITS
    خصوص
    0.07
    MainWindow
    0.07
     FilePath
    0.07
     wida
    0.07
     фир
    0.07
    彧
    0.07
    投稿
    0.07
     Gould
    0.07
    EMENT
    0.07
     SQLite
    0.07
    Act Density 0.007%

    No Known Activations