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

    Neuronpedia

    INDEX
    Explanations

    fulfill commitments and promises

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     asigur
    0.42
     jamb
    0.38
    刺
    0.38
     standards
    0.37
     acceptance
    0.37
     assicur
    0.37
     moulding
    0.37
    inoff
    0.36
     accommodation
    0.36
     veneer
    0.36
    POSITIVE LOGITS
     fulfilled
    1.13
     fulfillment
    1.07
     fulfill
    1.05
     fulfilment
    1.04
     fulfil
    1.02
    履行
    0.97
     cumpr
    0.95
    fulfilled
    0.93
     fulfills
    0.90
    fulfillment
    0.89
    Act Density 0.025%

    No Known Activations