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

    Neuronpedia

    INDEX
    Explanations

    Here's a breakdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ্ু
    1.17
    ্রয়
    0.97
    রিষ্ঠ
    0.96
     。,
    0.96
     লইয়া
    0.95
    пикир
    0.93
    িনবার্গ
    0.89
    <unused601>
    0.89
    䨘
    0.89
     、,
    0.89
    POSITIVE LOGITS
    '
    4.48
    ’
    4.40
    ´
    2.79
    \'
    2.31
    ʼ
    2.27
    ׳
    2.10
    ’
    2.03
    `
    2.00
    ′
    2.00
    ‘
    1.97
    Act Density 2.180%

    No Known Activations