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

    Neuronpedia

    INDEX
    Explanations

    Locations/place names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ContentType
    -0.07
    ious
    -0.06
    _about
    -0.06
    atron
    -0.06
     communicates
    -0.06
    umbnails
    -0.06
    精品
    -0.06
     longing
    -0.06
    setProperty
    -0.06
     inaugural
    -0.06
    POSITIVE LOGITS
     Almighty
    0.07
     Laur
    0.07
    曰
    0.06
     вывод
    0.06
     Laure
    0.06
     универ
    0.06
    hled
    0.06
     ❤
    0.06
     СССР
    0.06
     khiến
    0.06
    Act Density 0.010%

    No Known Activations