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

    Neuronpedia

    INDEX
    Explanations

    types of loans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ler
    0.43
     Lel
    0.42
    Lep
    0.42
     Lep
    0.41
    槨
    0.41
     heads
    0.39
     Ludwig
    0.39
     caracteres
    0.39
     Leopold
    0.38
     Leb
    0.38
    POSITIVE LOGITS
     loans
    1.47
     loan
    1.29
    loans
    1.28
     Loans
    1.21
    loan
    1.13
    Loans
    1.12
     लोन
    1.09
     Loan
    1.04
    贷款
    1.03
    Loan
    1.02
    Act Density 0.006%

    No Known Activations