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

    Neuronpedia

    INDEX
    Explanations

    Health and injuries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Chess
    -0.07
    itte
    -0.06
    .swap
    -0.06
     RAM
    -0.06
    Filter
    -0.06
    (sentence
    -0.06
    <Player
    -0.06
    ırı
    -0.06
    .Simple
    -0.06
    orption
    -0.06
    POSITIVE LOGITS
     Sq
    0.06
     SY
    0.06
    330
    0.06
    brıs
    0.06
     dudes
    0.06
     Browns
    0.06
    |m
    0.06
     rele
    0.06
    ivel
    0.06
    _iso
    0.06
    Act Density 0.033%

    No Known Activations