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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and subtraction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     reimag
    0.84
     minimalist
    0.82
     Kindle
    0.78
     Salesforce
    0.78
     Deloitte
    0.75
     cryptocur
    0.74
     cryptocurrency
    0.74
     Kaspersky
    0.74
     neoclassical
    0.72
     proactive
    0.72
    POSITIVE LOGITS
     (-
    1.21
     sqrt
    1.08
    (-
    1.05
    sqrt
    1.00
    <unused1984>
    0.96
     (−
    0.90
     √(
    0.86
     x
    0.86
     √
    0.85
    Sqrt
    0.85
    Act Density 0.942%

    No Known Activations