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

    Neuronpedia

    INDEX
    Explanations

    or

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    そして
    0.46
    および
    0.41
     এবং
    0.40
     nejen
    0.38
     البته
    0.36
     ಹಾಗೂ
    0.35
    srcset
    0.35
    និង
    0.34
     albeit
    0.34
    এবং
    0.34
    POSITIVE LOGITS
     veya
    0.71
     oppure
    0.66
     yoki
    0.62
     හෝ
    0.58
    或其他
    0.58
    なのか
    0.57
    หรือไม่
    0.57
    ?')
    0.55
     alebo
    0.55
    ؟
    0.55
    Act Density 0.687%

    No Known Activations