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

    Neuronpedia

    INDEX
    Explanations

    order of operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المن
    -0.74
    ַ
    -0.71
    הו
    -0.69
     len
    -0.69
    Shutdown
    -0.67
    addComponent
    -0.67
    기를
    -0.66
    )}_
    -0.66
    طط
    -0.66
    <0xA0>
    -0.66
    POSITIVE LOGITS
     PEM
    1.14
     getOrder
    1.10
     order
    1.04
     BOD
    1.02
    PEM
    0.96
     parentheses
    0.91
     Order
    0.90
     BED
    0.87
     acronym
    0.86
    BOD
    0.84
    Act Density 0.052%

    No Known Activations