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

    Neuronpedia

    INDEX
    Explanations

    pay

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     câ
    -0.07
    AMPLES
    -0.07
    Menu
    -0.07
    Elements
    -0.07
    estors
    -0.07
    _elements
    -0.07
    frastr
    -0.07
    anos
    -0.07
    amples
    -0.07
     institucional
    -0.07
    POSITIVE LOGITS
     debt
    0.10
     payment
    0.10
     accelerated
    0.09
     قرض
    0.09
     Debt
    0.09
     betaling
    0.09
     prioritize
    0.09
     pembayaran
    0.09
     wünsche
    0.09
     выплаты
    0.09
    Act Density 0.009%

    No Known Activations