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

    Neuronpedia

    INDEX
    Explanations

    loan decisions and approvals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    the
    0.78
    ли
    0.72
    ۔
    0.72
    al
    0.63
    ра
    0.60
    t
    0.60
     পরই
    0.59
     juncture
    0.59
    人
    0.59
    ol
    0.58
    POSITIVE LOGITS
    ↵
    0.91
     loans
    0.90
    م
    0.86
     Loans
    0.81
    س
    0.79
     Loan
    0.74
    Loans
    0.74
     borrowers
    0.72
    6
    0.70
     a
    0.68
    Act Density 0.005%

    No Known Activations