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

    Neuronpedia

    INDEX
    Explanations

    code delimiters and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    或其他
    0.47
    等
    0.46
     інших
    0.44
     প্রমুখ
    0.43
    }+...
    0.43
     आदि
    0.42
    等人
    0.39
    ?,?,
    0.38
    Secondly
    0.37
     sebagainya
    0.37
    POSITIVE LOGITS
     ხოლო
    0.49
     finally
    0.39
     infine
    0.37
     އަ
    0.36
     rubbish
    0.35
     Master
    0.35
     Ru
    0.35
    baru
    0.34
     Ku
    0.34
    └──
    0.33
    Act Density 0.132%

    No Known Activations