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

    Neuronpedia

    INDEX
    Explanations

    rate of occurence

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of rates—phrases expressing a quantity “per” unit of time (e.g. “units per minute,” “frames per second”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    service
    -0.06
    .Zero
    -0.06
    indexPath
    -0.06
    大
    -0.06
    .text
    -0.06
     riding
    -0.06
    _AA
    -0.06
     Communication
    -0.06
     shutting
    -0.06
     cJSON
    -0.06
    POSITIVE LOGITS
     evrop
    0.08
    		↵↵
    0.06
     Hexatrigesimal
    0.06
    егра
    0.06
     series
    0.06
    ogy
    0.06
    ฎ
    0.06
    >tagger
    0.06
    /↵
    0.06
     assorted
    0.06
    Act Density 0.019%

    No Known Activations