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

    Neuronpedia

    INDEX
    Explanations

    numbers following punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ninety
    1.24
    ９
    1.24
    9
    1.22
    <0xBF>
    1.20
     Ninety
    1.20
     ۹
    1.15
     Ninth
    1.03
     ९
    1.00
     девя
    0.99
    ۹
    0.98
    POSITIVE LOGITS
    <unused2>
    0.41
    জ্ঞা
    0.37
     नसी
    0.36
    >}</
    0.35
    benzo
    0.35
     deflate
    0.35
     hina
    0.34
     নি
    0.34
     rarity
    0.33
    िली
    0.33
    Act Density 0.035%

    No Known Activations