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

    Neuronpedia

    INDEX
    Explanations

    money, payments, rent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    de
    0.70
    der
    0.59
    da
    0.59
    ard
    0.58
    alt
    0.55
    att
    0.54
    den
    0.53
    ige
    0.52
    deen
    0.51
    ella
    0.51
    POSITIVE LOGITS
     refinance
    0.51
     reim
    0.49
     commut
    0.49
     seafront
    0.46
     beachfront
    0.46
     retir
    0.45
    רי
    0.45
    сси
    0.45
     комбина
    0.44
     refinancing
    0.44
    Act Density 0.006%

    No Known Activations