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

    Neuronpedia

    INDEX
    Explanations

    punctuation and code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }={
    1.60
    Ы
    1.46
     metų
    1.43
    н
    1.41
    𝘂
    1.41
    "<<
    1.32
     impor
    1.31
     gând
    1.30
    তম
    1.26
    Н
    1.23
    POSITIVE LOGITS
    _,
    1.59
    $-$,
    1.49
    ാ
    1.45
     //$
    1.44
    ع
    1.43
     avenues
    1.41
     ﺍﻟ
    1.41
    omitem
    1.40
    ियर्स
    1.31
     серд
    1.31
    Act Density 0.337%

    No Known Activations