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

    Neuronpedia

    INDEX
    Explanations

    credit, debt, income, tax, employment history

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     loans
    0.48
    loans
    0.48
     قرض
    0.48
    Loans
    0.44
     Loans
    0.41
     tarjetas
    0.40
    anging
    0.40
     пога
    0.40
     tarjeta
    0.39
     remedial
    0.38
    POSITIVE LOGITS
    ziest
    0.42
     Bauern
    0.39
     വ്യ
    0.38
     Capabilities
    0.38
     visualization
    0.38
     Dustin
    0.36
    issage
    0.36
    zną
    0.35
    完整的
    0.35
     Visualization
    0.35
    Act Density 0.010%

    No Known Activations