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

    Neuronpedia

    INDEX
    Explanations

    rising negative socio-economic indicators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     total
    0.99
     excessive
    0.92
    Total
    0.91
    total
    0.90
    Excess
    0.87
     tota
    0.85
     reduction
    0.84
     Total
    0.83
    Reduce
    0.82
     Reducing
    0.80
    POSITIVE LOGITS
     defaultConfig
    1.00
    prices
    0.90
     prices
    0.89
     PRICES
    0.84
     Prices
    0.84
     preços
    0.84
     Preise
    0.82
     आयकर
    0.81
     unemployed
    0.81
     sceptical
    0.80
    Act Density 0.028%

    No Known Activations