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

    Neuronpedia

    INDEX
    Explanations

    insurance types and applicability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     एल्गोरि
    0.72
     Claim
    0.70
     Aguas
    0.70
    unate
    0.70
    Claim
    0.68
     Claims
    0.66
     claim
    0.65
    vues
    0.65
    বাঁ
    0.64
     claims
    0.63
    POSITIVE LOGITS
     liability
    1.03
     renters
    1.01
     homeowner
    1.00
     homeowners
    0.97
     renter
    0.96
     Liability
    0.88
     Comprehensive
    0.88
    Comprehensive
    0.88
     comprehensive
    0.88
    Liability
    0.83
    Act Density 0.029%

    No Known Activations