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

    Neuronpedia

    INDEX
    Explanations

    addresses specific topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    า
    1.60
    '
    1.50
    -
    1.48
    .
    1.46
    ü
    1.36
    ก
    1.31
    ik
    1.30
    1.27
    ла
    1.27
    ন
    1.25
    POSITIVE LOGITS
    ﻮ
    1.16
    вається
    1.06
    getLong
    1.05
    ুস
    1.00
     مؤرشف
    0.98
    ‌ها
    0.98
     Samaj
    0.98
    দের
    0.97
    는다
    0.97
    Romans
    0.97
    Act Density 0.016%

    No Known Activations