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

    Neuronpedia

    INDEX
    Explanations

    reinforcement and behavior modification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    叡
    0.45
     gigantes
    0.43
    Hö
    0.42
     രാജ്യ
    0.42
    森林
    0.42
     مدی
    0.41
    hosting
    0.41
    hostname
    0.41
    ամ
    0.41
     અ
    0.41
    POSITIVE LOGITS
     Behavioral
    0.66
     reward
    0.65
     Reward
    0.63
     behavioral
    0.61
     incentive
    0.60
     rewards
    0.57
    Reward
    0.55
     Rewards
    0.55
    Behavior
    0.53
     Behavior
    0.52
    Act Density 0.052%

    No Known Activations