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

    Neuronpedia

    INDEX
    Explanations

    religion politics culture social discourse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     동일
    0.44
    ①
    0.44
     फॉलो
    0.44
     rendezvous
    0.41
     twee
    0.41
    appings
    0.40
     gevolg
    0.39
     없
    0.38
     ফলো
    0.38
     ketiga
    0.38
    POSITIVE LOGITS
    Religion
    0.37
    政治
    0.36
    ```
    0.35
    宏
    0.35
    Ά
    0.34
     **
    0.33
    バス
    0.33
     Sosial
    0.33
     فرهنگ
    0.33
    宗教
    0.32
    Act Density 0.225%

    No Known Activations