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

    Neuronpedia

    INDEX
    Explanations

    Mathematical support

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of a function’s support or related set‐theoretic LaTeX expressions (e.g. “support,” “subset,” “supₚ,” and similar notation describing where a function is nonzero).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Hooks
    -0.08
    [table
    -0.07
    .between
    -0.07
    Banner
    -0.07
    (cookie
    -0.07
    .Nodes
    -0.07
     Conce
    -0.07
    ступ
    -0.07
    -banner
    -0.07
    Cluster
    -0.07
    POSITIVE LOGITS
     معت
    0.08
     виб
    0.06
    .LayoutInflater
    0.06
    =<?
    0.06
    .opacity
    0.06
     financially
    0.06
     zg
    0.06
     repl
    0.06
     reprint
    0.06
     advertis
    0.06
    Act Density 0.003%

    No Known Activations