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

    Neuronpedia

    INDEX
    Explanations

    annual interest rates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    髌
    0.54
    otherapie
    0.53
     轻
    0.49
     〢
    0.48
    owneri
    0.48
    萜
    0.48
    Pyrimidine
    0.47
    Penumpang
    0.47
    超时
    0.47
     важли
    0.46
    POSITIVE LOGITS
     rate
    0.82
     rates
    0.77
     annual
    0.69
     yearly
    0.59
     Rate
    0.59
     Rates
    0.57
     annum
    0.55
    Rates
    0.55
     annually
    0.53
     RATE
    0.53
    Act Density 0.028%

    No Known Activations