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

    Neuronpedia

    INDEX
    Explanations

    PHP code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IMITER
    -0.07
    wner
    -0.07
    _SOCKET
    -0.07
     LT
    -0.06
     guarante
    -0.06
          ↵      ↵
    -0.06
    луата
    -0.06
    :",↵
    -0.06
     slov
    -0.06
     zz
    -0.06
    POSITIVE LOGITS
     Communications
    0.07
     recuper
    0.07
     challenged
    0.07
    Classification
    0.06
    <?>
    0.06
    (class
    0.06
     секрет
    0.06
     photographs
    0.06
     مدير
    0.06
    /REC
    0.06
    Act Density 0.002%

    No Known Activations