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

    Neuronpedia

    INDEX
    Explanations

    financial data issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    The
    0.31
    ച
    0.30
     چهار
    0.30
    Seven
    0.30
     მდ
    0.30
    க்தி
    0.29
    Experiment
    0.29
    Dé
    0.29
    Three
    0.29
    観察
    0.29
    POSITIVE LOGITS
     invoices
    0.49
     payments
    0.45
     wallets
    0.44
     invoice
    0.43
     financials
    0.42
     data
    0.41
     paycheck
    0.41
     assets
    0.40
     taxpayers
    0.40
     taxpayer
    0.39
    Act Density 0.000%

    No Known Activations