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

    Neuronpedia

    INDEX
    Explanations

    Quotations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    寿
    -0.06
    >"
    -0.06
    中国
    -0.06
    %.
    -0.06
     merged
    -0.06
     cách
    -0.06
     Transformer
    -0.06
     nedir
    -0.06
    ║
    -0.06
    庄
    -0.06
    POSITIVE LOGITS
    -road
    0.07
    .ColumnName
    0.07
    erek
    0.06
     Notification
    0.06
    Serialization
    0.06
     Bran
    0.06
    ิ้
    0.06
    .Gen
    0.06
     растений
    0.06
    _FORMAT
    0.06
    Act Density 0.019%

    No Known Activations