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

    Neuronpedia

    INDEX
    Explanations

    factors leading to outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    0.29
    ،
    0.25
    （
    0.24
     ("
    0.23
     (“
    0.23
     («
    0.23
    །
    0.22
    ,(
    0.22
    ：
    0.21
    ۔
    0.21
    POSITIVE LOGITS
     in
    0.28
    that
    0.23
    in
    0.23
    on
    0.21
     that
    0.21
     которые
    0.21
    在
    0.21
     as
    0.21
    ที่
    0.20
    with
    0.19
    Act Density 0.372%

    No Known Activations