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

    Neuronpedia

    INDEX
    Explanations

    high volatility risk

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    মোট
    0.73
     പൊലീസ്
    0.73
     Bankruptcy
    0.72
    Ent
    0.72
    Cann
    0.72
     Fet
    0.71
    Sales
    0.71
    ney
    0.70
    Earnings
    0.70
    Statistics
    0.69
    POSITIVE LOGITS
     limit
    0.92
    limit
    0.91
    Limit
    0.85
     limiting
    0.84
     Limit
    0.83
     LIMIT
    0.71
    极限
    0.68
     variance
    0.68
    лү
    0.68
    ळ
    0.66
    Act Density 0.004%

    No Known Activations