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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     digits
    -0.09
    digits
    -0.08
    Digits
    -0.08
     ×
    -0.07
    quist
    -0.07
    ianchi
    -0.07
    ouncycastle
    -0.07
    ociated
    -0.07
     Pascal
    -0.07
     стороне
    -0.07
    POSITIVE LOGITS
    总结
    0.14
     recap
    0.10
    まとめ
    0.10
     farewell
    0.10
     gratitude
    0.09
     감사
    0.09
     summarize
    0.09
     dissemin
    0.09
     agrade
    0.09
    感谢
    0.09
    Act Density 0.012%

    No Known Activations