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

    Neuronpedia

    INDEX
    Explanations

    tax deductions and allowances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    S
    0.74
     me
    0.72
     I
    0.71
    z
    0.68
    !
    0.64
    ز
    0.64
    I
    0.63
    L
    0.62
     such
    0.61
    4
    0.61
    POSITIVE LOGITS
     deductions
    0.84
     deductible
    0.84
     налого
    0.84
     deduct
    0.78
     taxes
    0.74
     आयकर
    0.73
     expenses
    0.72
     spese
    0.71
     टैक्स
    0.71
     entitlements
    0.70
    Act Density 0.065%

    No Known Activations