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

    Neuronpedia

    INDEX
    Explanations

    size specifications and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    কে
    1.33
     in
    1.25
    ندي
    1.11
    ري
    1.10
    在
    1.06
    С
    1.04
    も
    1.02
    ین
    0.97
    }{
    0.94
    ве
    0.93
    POSITIVE LOGITS
    ur
    1.71
    ar
    1.63
    il
    1.55
    an
    1.52
    er
    1.44
    ни
    1.30
    ul
    1.26
    ert
    1.22
     size
    1.16
    on
    1.16
    Act Density 0.039%

    No Known Activations