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

    Neuronpedia

    INDEX
    Explanations

    m or M identifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    p
    1.53
    in
    1.50
    '
    1.23
    ak
    1.22
    is
    1.20
    am
    1.13
    are
    1.12
    em
    1.07
    nál
    1.05
    inia
    1.05
    POSITIVE LOGITS
    ра
    1.02
    ため
    0.99
    ри
    0.97
    ร
    0.94
     outstretched
    0.91
    ],
    0.90
    くちゃ
    0.88
    ذ
    0.88
    ז
    0.88
    ו
    0.88
    Act Density 0.388%

    No Known Activations