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

    Neuronpedia

    INDEX
    Explanations

    Rules, terms, and conditions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     двигател
    -0.07
    --,
    -0.07
     drone
    -0.07
    剡
    -0.07
    +(
    -0.07
     mandatory
    -0.06
    realDonaldTrump
    -0.06
     Schneider
    -0.06
     даже
    -0.06
     military
    -0.06
    POSITIVE LOGITS
     verb
    0.07
    래
    0.07
    膠
    0.07
    荒
    0.07
    /cart
    0.07
    _fps
    0.07
     crib
    0.06
     ifdef
    0.06
     תה
    0.06
    /bar
    0.06
    Act Density 0.112%

    No Known Activations