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

    Neuronpedia

    INDEX
    Explanations

    Discount factor (RL)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    中心
    -0.08
    agnes
    -0.08
     centrally
    -0.08
     Dar
    -0.08
    anos
    -0.08
    (center
    -0.07
     centrum
    -0.07
     केंद्र
    -0.07
     archa
    -0.07
     centro
    -0.07
    POSITIVE LOGITS
    Replay
    0.10
    Recursive
    0.10
     recursion
    0.09
     Replay
    0.09
     replay
    0.09
     sequel
    0.08
    recursive
    0.08
     continuation
    0.08
     recursive
    0.08
    -rec
    0.08
    Act Density 0.002%

    No Known Activations