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

    Neuronpedia

    INDEX
    Explanations

    importance and warnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     धाराओं
    0.40
     \{
    0.39
     เด้อ
    0.37
    रियल
    0.37
     Ljub
    0.37
     rougeâtre
    0.37
    Libra
    0.36
    嘰
    0.36
    ন্ত্রণ
    0.36
    धिकारिक
    0.36
    POSITIVE LOGITS
     Mann
    0.41
     특히
    0.40
    重要的是
    0.39
     مهم
    0.39
    웨
    0.38
    重要的
    0.38
     Importantly
    0.37
     belangrijke
    0.37
     महत्वपूर्ण
    0.36
     ważne
    0.36
    Act Density 0.013%

    No Known Activations