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

    Neuronpedia

    INDEX
    Explanations

    forcement/强化

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     obituary
    -0.08
    érios
    -0.08
    credits
    -0.08
     fonte
    -0.08
     إليه
    -0.08
     dc
    -0.08
     technologically
    -0.08
    Virgin
    -0.07
    েপ
    -0.07
     leon
    -0.07
    POSITIVE LOGITS
    训
    0.09
     Pac
    0.09
    Maze
    0.09
    QL
    0.08
    Pac
    0.08
     gambling
    0.08
    .reward
    0.08
     rewards
    0.08
     entrenamiento
    0.08
     मिला
    0.08
    Act Density 0.003%

    No Known Activations