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

    Neuronpedia

    INDEX
    Explanations

    the specific noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    0.17
    with
    0.16
     ,
    0.15
    ("
    0.15
    ），
    0.15
    r
    0.15
     (
    0.15
    also
    0.15
    ',
    0.15
    (
    0.15
    POSITIVE LOGITS
     idea
    0.18
     intricacies
    0.17
     onus
    0.17
    odore
    0.16
     intric
    0.15
     crux
    0.15
     specifics
    0.15
    atrical
    0.15
     inev
    0.15
     repercussions
    0.15
    Act Density 1.916%

    No Known Activations