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

    Neuronpedia

    INDEX
    Explanations

    stocks and investments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     payments
    0.84
     bloated
    0.84
     fines
    0.78
     leaks
    0.76
    ↵
    0.73
     Payments
    0.71
     payment
    0.71
     debts
    0.71
    َنْ
    0.70
    忧
    0.69
    POSITIVE LOGITS
    c
    1.02
    を用いた
    0.93
    ch
    0.86
    x
    0.81
     Spectroscopy
    0.80
    z
    0.80
    UNSIGNED
    0.79
    ied
    0.79
    cador
    0.79
     의한
    0.78
    Act Density 0.227%

    No Known Activations