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

    Neuronpedia

    INDEX
    Explanations

    statement credits and 'credited'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     paid
    0.46
    paid
    0.44
     Paid
    0.44
     induction
    0.42
    enties
    0.41
     paiement
    0.41
     récomp
    0.41
     Rewards
    0.40
     rewards
    0.39
     reward
    0.39
    POSITIVE LOGITS
     credits
    1.00
     Credits
    0.97
    credits
    0.95
    Credits
    0.91
     credited
    0.71
     cred
    0.67
     Créd
    0.66
     créd
    0.64
     CRED
    0.64
     créditos
    0.64
    Act Density 0.014%

    No Known Activations