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

    Neuronpedia

    INDEX
    Explanations

    ine

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ANG
    -0.07
     né
    -0.07
     różne
    -0.07
    أنشطة
    -0.07
    fgang
    -0.06
    Extend
    -0.06
     zostać
    -0.06
    來自
    -0.06
     erfolgreich
    -0.06
    אור
    -0.06
    POSITIVE LOGITS
    .timer
    0.09
     shipment
    0.08
    轿车
    0.07
     voters
    0.07
    yny
    0.07
     reordered
    0.07
    elcome
    0.07
    (drop
    0.07
     Roberts
    0.07
    咱们
    0.07
    Act Density 0.001%

    No Known Activations