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

    Neuronpedia

    INDEX
    Explanations

    OpenAI URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cepat
    0.46
    敒
    0.42
    シングル
    0.42
     ઝડ
    0.41
     fastest
    0.41
     cable
    0.40
    Chicken
    0.40
     Vegetables
    0.39
     ชี
    0.39
     Миха
    0.38
    POSITIVE LOGITS
     OpenAI
    0.50
     openai
    0.44
     ней
    0.42
     بشر
    0.42
    qua
    0.40
    openai
    0.40
    тей
    0.38
     Traum
    0.38
    量子
    0.38
    ্সি
    0.38
    Act Density 0.006%

    No Known Activations