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

    Neuronpedia

    INDEX
    Explanations

    refunds and returns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ೂರ
    0.77
     bursts
    0.74
    ccio
    0.69
     steig
    0.69
     gaps
    0.69
     entrances
    0.67
     beaming
    0.66
     Lockhart
    0.66
     அதிகரிக்கும்
    0.66
     yawn
    0.65
    POSITIVE LOGITS
    Refund
    2.33
     refund
    2.20
     refunds
    2.19
    refund
    2.11
     Refund
    2.07
     Refunds
    1.97
     refunded
    1.97
     remboursement
    1.70
     reembolso
    1.56
    Undo
    1.56
    Act Density 0.103%

    No Known Activations