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

    Neuronpedia

    INDEX
    Explanations

    order transaction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     preparación
    0.41
     interruptions
    0.41
     interruption
    0.41
    总理
    0.40
    Interrupt
    0.40
     préparation
    0.39
     détermination
    0.38
    πέ
    0.37
     języ
    0.36
    尽
    0.36
    POSITIVE LOGITS
     Compare
    0.46
     transact
    0.44
     TRANSACTION
    0.44
    Compare
    0.44
     Transaction
    0.43
    Transaction
    0.43
    टिक
    0.42
    ogon
    0.41
     compare
    0.41
     transactional
    0.41
    Act Density 0.001%

    No Known Activations