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

    Neuronpedia

    INDEX
    Explanations

    centroids

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of the k-means clustering algorithm and its related terminology (e.g. “KMeans,” “means,” “clusters,” “centroids,” “cluster centers,” and the number of clusters”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _quit
    -0.07
    paralle
    -0.07
     archivos
    -0.06
     limbs
    -0.06
    違
    -0.06
    	LOG
    -0.06
    Vintage
    -0.06
    _texture
    -0.06
     mult
    -0.06
     Redux
    -0.06
    POSITIVE LOGITS
    startsWith
    0.06
    ｀
    0.06
    ژن
    0.06
    "name
    0.06
    (Position
    0.06
     stabbing
    0.06
    $criteria
    0.06
    lardan
    0.06
    RGBO
    0.06
     agility
    0.06
    Act Density 0.005%

    No Known Activations