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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SMART
    -0.10
     weighing
    -0.09
     weigh
    -0.09
    护
    -0.08
     repairs
    -0.08
     protective
    -0.08
     hospice
    -0.08
     weighed
    -0.08
     outweigh
    -0.08
     redesign
    -0.08
    POSITIVE LOGITS
     Uran
    0.08
     Invoke
    0.08
     вызывает
    0.08
     याद
    0.08
     annoy
    0.08
     Longitude
    0.08
     radians
    0.08
     oscillator
    0.08
     Addresses
    0.08
     Orb
    0.08
    Act Density 0.016%

    No Known Activations