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

    Neuronpedia

    INDEX
    Explanations

    academy award

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rewards
    1.37
    rewards
    1.27
     reward
    1.23
    Rewards
    1.21
     rewarded
    1.18
     Rewards
    1.18
    Reward
    1.16
    reward
    1.15
     Reward
    1.13
     recompens
    1.11
    POSITIVE LOGITS
     Award
    1.57
     Awards
    1.45
    Award
    1.43
     AWARD
    1.42
     award
    1.38
    award
    1.36
    Awards
    1.31
     अवार्ड
    1.22
     awards
    1.19
    awards
    1.18
    Act Density 0.011%

    No Known Activations