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

    Neuronpedia

    INDEX
    Explanations

    medical conditions and specific entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    e
    1.34
    l
    1.34
    و
    1.23
    وپ
    1.20
    IN
    1.15
    ্স
    1.15
    と思います
    1.13
    b
    1.13
    uating
    1.08
    uot
    1.07
    POSITIVE LOGITS
     avec
    1.25
     with
    1.21
     from
    1.17
    1.13
     begon
    1.09
    কে
    1.09
     distinguishes
    1.08
     които
    1.05
     із
    1.05
     erreichte
    1.05
    Act Density 0.472%

    No Known Activations