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

    Neuronpedia

    INDEX
    Explanations

    numbers, dates, learning, or factual information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disbursements
    0.47
     facades
    0.45
     faucets
    0.45
     deliveries
    0.44
     punctures
    0.43
     nozzles
    0.43
     privé
    0.42
     mails
    0.42
     invitations
    0.42
     clarifications
    0.42
    POSITIVE LOGITS
     للد
    0.54
     Gospel
    0.48
     segí
    0.48
    统
    0.46
    မြင်
    0.45
     للح
    0.44
     Current
    0.43
     Enseñanza
    0.43
     Choose
    0.43
     nær
    0.43
    Act Density 0.003%

    No Known Activations