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

    Neuronpedia

    INDEX
    Explanations

    growth and development

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝘻
    2.28
    𝘬
    2.16
     bună
    2.04
    рке
    1.98
    graduation
    1.96
     annet
    1.90
    '}}>
    1.89
     andet
    1.88
     "\\
    1.88
     tel
    1.88
    POSITIVE LOGITS
    ן
    3.52
    م
    2.51
    शील
    2.45
    ន៍
    2.33
    alanine
    2.30
    dan
    2.21
     событий
    2.16
    की
    2.14
    ્ષ
    2.13
     ক্ষ
    2.03
    Act Density 0.252%

    No Known Activations