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

    Neuronpedia

    INDEX
    Explanations

    asymptotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .rating
    -0.08
     welfare
    -0.08
     αντα
    -0.08
    ęt
    -0.08
    արկ
    -0.08
     Tibetan
    -0.08
     agreeing
    -0.08
    يل
    -0.08
    _rating
    -0.08
     Welfare
    -0.07
    POSITIVE LOGITS
     poles
    0.09
     Locations
    0.09
    Zeros
    0.09
     outages
    0.09
     symptomatic
    0.09
     zeros
    0.08
     blockage
    0.08
    域
    0.08
     obstruction
    0.08
     removable
    0.08
    Act Density 0.016%

    No Known Activations