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

    Neuronpedia

    INDEX
    Explanations

    theoretical limits

    np_max-act · gemini-2.0-flash

    This neuron detects expressions of algorithmic time complexity, particularly big-O notation and related complexity terms.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     alış
    -0.07
    ки
    -0.06
    ิตย
    -0.06
    بینی
    -0.06
    Fail
    -0.06
     Maxim
    -0.06
     approximation
    -0.06
     root
    -0.06
    Intent
    -0.06
    723
    -0.06
    POSITIVE LOGITS
     bottleneck
    0.07
    :'',↵
    0.07
     cq
    0.07
    )،
    0.07
     )),↵
    0.06
     고
    0.06
    .Il
    0.06
     comps
    0.06
     MediaTek
    0.06
    ||
    0.06
    Act Density 0.024%

    No Known Activations