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

    Neuronpedia

    INDEX
    Explanations

    python library names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    or
    1.28
    ibid
    1.26
    >=</
    1.21
    walled
    1.20
    ä
    1.17
    ɡ
    1.16
    eny
    1.14
     verschied
    1.14
    های
    1.13
     seule
    1.13
    POSITIVE LOGITS
    其他
    1.68
    ل
    1.61
    дир
    1.41
    增长
    1.37
    чки
    1.35
    ০০
    1.35
     phép
    1.34
    gruppe
    1.34
    نيا
    1.33
    秕
    1.29
    Act Density 0.003%

    No Known Activations