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

    Neuronpedia

    INDEX
    Explanations

    commas and quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ವಿದ್ಯ
    -0.08
     ಊ
    -0.07
     ತಿಂ
    -0.07
     rowspan
    -0.07
     కాల
    -0.07
     ಹೊ
    -0.07
     Allí
    -0.07
     ಕಲ
    -0.07
     seguida
    -0.07
     పార
    -0.07
    POSITIVE LOGITS
    等等
    0.08
     عبار
    0.08
    。所以
    0.08
    god
    0.08
     प्रतिष्ठ
    0.08
    Keywords
    0.07
     greek
    0.07
     आदि
    0.07
     говорится
    0.07
     aggregator
    0.07
    Act Density 0.043%

    No Known Activations