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

    Neuronpedia

    INDEX
    Explanations

    quotation marks and pauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﺭ
    1.59
     ಸಾವಿರ
    1.55
    াহিনী
    1.47
    ﻯ
    1.45
    ﺩ
    1.43
    ﻥ
    1.42
    หมาย
    1.38
    ﻡ
    1.37
    ﻝ
    1.36
     épars
    1.35
    POSITIVE LOGITS
    '
    1.68
     '
    1.47
     \"
    1.41
    。
    1.34
    .'
    1.30
    ('
    1.27
    ।
    1.26
     "
    1.24
    1.21
    ),
    1.20
    Act Density 0.020%

    No Known Activations