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

    Neuronpedia

    INDEX
    Explanations

    budget and financial policies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wavy
    0.55
     disgraced
    0.53
     clumsy
    0.53
     untouched
    0.51
     dehydrated
    0.51
     synchrotron
    0.51
     awkwardly
    0.51
     terrified
    0.50
     squint
    0.50
     slowed
    0.50
    POSITIVE LOGITS
     budgets
    0.74
     budgetary
    0.71
     बजट
    0.68
    Budget
    0.68
     বাজেট
    0.68
     budgeting
    0.68
    Risk
    0.66
    Policies
    0.65
    Compliance
    0.65
     Policies
    0.64
    Act Density 0.176%

    No Known Activations