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

    Neuronpedia

    INDEX
    Explanations

    degree, tests, keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    िरपेक्ष
    0.41
    पृथ
    0.40
     मानसून
    0.38
     Кай
    0.38
    izards
    0.37
     فونٹ
    0.37
     महत्त्वा
    0.37
     इक्वेशन
    0.36
    鴻
    0.36
     работаю
    0.35
    POSITIVE LOGITS
    </h4>
    0.49
    <h4>
    0.42
     ib
    0.41
     streaming
    0.38
    View
    0.38
     לפי
    0.38
    match
    0.37
     филь
    0.37
    根據
    0.36
    streaming
    0.35
    Act Density 0.000%

    No Known Activations