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

    Neuronpedia

    INDEX
    Explanations

    money or payment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ολο
    0.42
     khả
    0.41
    ოლოდ
    0.38
     sẵn
    0.37
     способны
    0.37
    ऊं
    0.36
    ्रेस
    0.36
     ஆராய்ச்ச
    0.36
    slaught
    0.36
     परिभाषित
    0.35
    POSITIVE LOGITS
     pagamento
    0.46
     dinero
    0.46
     pubblici
    0.45
     during
    0.44
     payment
    0.44
     fick
    0.44
     papier
    0.44
     zakup
    0.43
     coupon
    0.42
     directories
    0.42
    Act Density 0.005%

    No Known Activations