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

    Neuronpedia

    INDEX
    Explanations

    Japanese and English text segments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    asjonen
    0.57
     brutality
    0.56
    тинг
    0.55
     gratefully
    0.54
    madı
    0.52
     boldness
    0.52
    тин
    0.51
    мага
    0.50
    alek
    0.50
    чей
    0.50
    POSITIVE LOGITS
    _
    0.78
    $
    0.62
    {
    0.61
    ET
    0.59
    七
    0.57
    at
    0.57
    _{
    0.56
    大
    0.55
    い
    0.55
    将
    0.54
    Act Density 0.006%

    No Known Activations