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

    Neuronpedia

    INDEX
    Explanations

    neural networks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -validation
    -0.07
     cytok
    -0.07
     صنعتی
    -0.06
    .accel
    -0.06
    اريخ
    -0.06
     ucfirst
    -0.06
    _AD
    -0.06
    gorit
    -0.06
    .HOUR
    -0.06
    .Results
    -0.06
    POSITIVE LOGITS
     AssemblyProduct
    0.07
     농
    0.07
     applicable
    0.07
     pups
    0.07
     expended
    0.06
    dy
    0.06
    pq
    0.06
    324
    0.06
    pin
    0.06
    jen
    0.06
    Act Density 0.001%

    No Known Activations