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

    Neuronpedia

    INDEX
    Explanations

    names with M initial

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ak
    1.80
    are
    1.63
    '
    1.55
    in
    1.49
    p
    1.44
    itt
    1.39
    uk
    1.34
    oh
    1.30
    am
    1.29
    IN
    1.29
    POSITIVE LOGITS
    ו
    1.40
    ;
    1.25
    ри
    1.18
    ],
    1.16
    t
    1.15
    }
    1.14
    تها
    1.12
     pajama
    1.07
    くちゃ
    1.06
    त
    1.06
    Act Density 4.134%

    No Known Activations