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

    Neuronpedia

    INDEX
    Explanations

    stock photos and illustrations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     시스템
    -0.06
     dementia
    -0.06
     licenses
    -0.06
     orderly
    -0.06
     walked
    -0.06
    slave
    -0.06
     Streams
    -0.06
    buckets
    -0.06
     Paste
    -0.06
     compounds
    -0.06
    POSITIVE LOGITS
    nej
    0.07
     narration
    0.06
     наш
    0.06
    ’ят
    0.06
     hecho
    0.06
    _tri
    0.06
    ати
    0.06
    etí
    0.06
     enim
    0.06
    ți
    0.06
    Act Density 0.034%

    No Known Activations