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

    Neuronpedia

    INDEX
    Explanations

    Chebyshev polynomials

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     сексу
    -0.09
     Motel
    -0.09
    tenant
    -0.08
    street
    -0.08
     motel
    -0.08
     heterosexual
    -0.08
     condom
    -0.08
    'hôtel
    -0.08
     оформ
    -0.08
     grieving
    -0.08
    POSITIVE LOGITS
     ffi
    0.10
     sampling
    0.09
     roots
    0.08
    Sampling
    0.08
     weights
    0.08
     LLVM
    0.08
     weighting
    0.08
    Roots
    0.08
     GCC
    0.08
     Sampling
    0.08
    Act Density 0.011%

    No Known Activations