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

    Neuronpedia

    INDEX
    Explanations

    data analysis and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     terça
    -0.08
     Seating
    -0.08
    -FIRST
    -0.08
     doare
    -0.08
    ,json
    -0.08
    (photo
    -0.08
     mande
    -0.08
     sns
    -0.08
    材料
    -0.08
    照片
    -0.08
    POSITIVE LOGITS
    Income
    0.08
    த
    0.08
    سط
    0.07
    ความ
    0.07
    வே
    0.07
     USSR
    0.07
    0.07
    Money
    0.07
    طي
    0.07
    Dollar
    0.07
    Act Density 0.001%
    No Known Activations