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

    Neuronpedia

    INDEX
    Explanations

    tournament selection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    plugins
    -0.08
    .Managed
    -0.08
    мас
    -0.08
    -0.08
    Manip
    -0.08
     என்ப
    -0.07
     hydrochlor
    -0.07
    anez
    -0.07
    ınca
    -0.07
     stopp
    -0.07
    POSITIVE LOGITS
     randomly
    0.09
    Sampling
    0.09
     sampling
    0.09
     Pair
    0.08
     Performer
    0.08
     Betting
    0.08
    Tournament
    0.08
    Wheel
    0.08
    sampling
    0.08
    _sampling
    0.08
    Act Density 0.001%

    No Known Activations