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

    Neuronpedia

    INDEX
    Explanations

    money making or how much money

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ఫ్
    0.55
     объема
    0.53
    utherland
    0.52
    ak
    0.51
    𝙘
    0.51
    snacks
    0.51
    𝙙
    0.51
    駑
    0.48
    ঵
    0.47
     непо
    0.47
    POSITIVE LOGITS
     money
    1.09
     Money
    1.05
    Money
    0.97
    钱
    0.96
     MONEY
    0.86
    money
    0.82
    錢
    0.81
     dinero
    0.81
     dinheiro
    0.79
     డబ్బు
    0.75
    Act Density 0.062%

    No Known Activations