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

    Neuronpedia

    INDEX
    Explanations

    data processing

    np_max-act · gemini-2.0-flash

    The neuron activates on words referring to data preprocessing—specifically “processed” (and its variants like “preprocessed”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     spray
    -0.08
     bolster
    -0.07
    .Query
    -0.06
     Porsche
    -0.06
     reputed
    -0.06
     CAST
    -0.06
     mutual
    -0.06
    -west
    -0.06
    icer
    -0.06
     〉
    -0.06
    POSITIVE LOGITS
     ба
    0.07
     Verified
    0.06
    Ế
    0.06
    -separated
    0.06
    HTTPRequestOperation
    0.06
    徳
    0.06
    ViewInit
    0.06
     ])↵
    0.06
     -----↵
    0.06
    (lr
    0.06
    Act Density 0.050%

    No Known Activations