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

    Neuronpedia

    INDEX
    Explanations

    non-alphanumeric symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    percentage
    -0.07
     DOS
    -0.07
    ccording
    -0.07
    illo
    -0.06
    \Query
    -0.06
    PUTE
    -0.06
    地区
    -0.06
    Descriptions
    -0.06
    ，小
    -0.06
     obed
    -0.06
    POSITIVE LOGITS
    opsis
    0.07
     الخارج
    0.07
     مختلف
    0.07
     heat
    0.06
    
    0.06
     sayılı
    0.06
     Projekt
    0.06
    iêng
    0.06
     surtout
    0.06
     Daha
    0.06
    Act Density 0.032%

    No Known Activations