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

    Neuronpedia

    INDEX
    Explanations

    interest rates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     विस्फोटक
    0.43
     дэ
    0.43
     உதவிய
    0.43
     exag
    0.41
    plasia
    0.41
     अपमान
    0.39
     ঔষধ
    0.39
    ደጋ
    0.39
     विक्रेता
    0.38
    貧
    0.38
    POSITIVE LOGITS
     rates
    0.69
     Rates
    0.63
    Rates
    0.52
     दरों
    0.50
     RATES
    0.49
     rate
    0.47
    rates
    0.47
     tasas
    0.47
     locks
    0.46
    offer
    0.44
    Act Density 0.047%

    No Known Activations