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

    Neuronpedia

    INDEX
    Explanations

    parts of words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    0.62
    ↵↵
    0.61
    ’
    0.59
    ↵
    0.50
    IA
    0.47
     beberapa
    0.46
    ams
    0.42
    อร์
    0.42
     layak
    0.41
    参见
    0.41
    POSITIVE LOGITS
    dır
    0.70
    ى
    0.69
    ي
    0.63
    но
    0.59
    ية
    0.58
    u
    0.55
    us
    0.54
    <0x80>
    0.52
     in
    0.52
    ку
    0.52
    Act Density 0.049%

    No Known Activations