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

    Neuronpedia

    INDEX
    Explanations

    XML tags or elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    el
    1.73
    м
    1.67
    ن
    1.58
    स्पति
    1.55
    ্টি
    1.52
    ै
    1.52
    ্প
    1.49
    ially
    1.48
    感じ
    1.47
    م
    1.47
    POSITIVE LOGITS
    AnalyzeAction
    1.60
     وعلى
    1.42
    ᴊ
    1.42
    ></
    1.41
     izquierdo
    1.41
    ]">
    1.41
    MiddleLine
    1.41
    勖
    1.39
    day
    1.38
    ᴅ
    1.38
    Act Density 0.018%

    No Known Activations