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

    Neuronpedia

    INDEX
    Explanations

    import statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    il
    0.88
    (
    0.85
    \%,
    0.78
    m
    0.77
    \
    0.75
     which
    0.75
    c
    0.73
     But
    0.73
    na
    0.72
    s
    0.72
    POSITIVE LOGITS
    τή
    1.02
    ای
    0.89
     tamaños
    0.79
    ธ
    0.78
    տ
    0.75
    𝚝
    0.75
    ﭥ
    0.73
    𝒚
    0.72
    тон
    0.71
    тус
    0.71
    Act Density 0.003%

    No Known Activations