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

    Neuronpedia

    INDEX
    Explanations

    named principles and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    isure
    0.47
    icine
    0.47
    मतौर
    0.47
     当然
    0.47
     Архив
    0.46
    azia
    0.45
    undur
    0.45
    ссив
    0.44
     архив
    0.44
     호텔
    0.44
    POSITIVE LOGITS
     balances
    0.50
     calculations
    0.48
     discrepancies
    0.48
     formula
    0.46
     balance
    0.46
     calculated
    0.45
    公式
    0.44
     computation
    0.42
     flawed
    0.42
    computation
    0.42
    Act Density 0.002%

    No Known Activations