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

    Neuronpedia

    INDEX
    Explanations

    Body scan meditation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    n
    2.11
    g
    1.98
    i
    1.96
    c
    1.93
    p
    1.90
    m
    1.88
    en
    1.73
    v
    1.66
    on
    1.64
    r
    1.60
    POSITIVE LOGITS
    檚
    1.63
    тов
    1.56
    %',
    1.42
     ребен
    1.36
     Flü
    1.34
    釟
    1.32
    Etudes
    1.31
     человеком
    1.30
    ется
    1.29
    มีการ
    1.29
    Act Density 1.797%

    No Known Activations