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

    Neuronpedia

    INDEX
    Explanations

    twe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     summon
    -0.07
    =re
    -0.07
    Pane
    -0.07
     Melissa
    -0.06
     Ug
    -0.06
    stral
    -0.06
    avourites
    -0.06
     persistent
    -0.06
    .annot
    -0.06
     官
    -0.06
    POSITIVE LOGITS
     performans
    0.07
     세상
    0.07
    $body
    0.07
     hành
    0.06
     partager
    0.06
    šit
    0.06
    .getDescription
    0.06
    -hooks
    0.06
     نرم
    0.06
    .backward
    0.06
    Act Density 0.018%

    No Known Activations