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

    Neuronpedia

    INDEX
    Explanations

    xmin

    np_max-act · gemini-2.0-flash

    The neuron never fires on any of the XML‐style annotation markup or numeric fields in these examples – in other words, it is effectively inactive on this structured metadata and does not detect any recurring text pattern here.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    績
    -0.07
     mluv
    -0.06
     flexGrow
    -0.06
     rebounds
    -0.06
    aData
    -0.06
     Scots
    -0.06
    hotel
    -0.06
    /temp
    -0.06
     Illinois
    -0.06
     dnů
    -0.06
    POSITIVE LOGITS
    xmax
    0.07
    xmin
    0.07
    ance
    0.07
    sumer
    0.07
     vinc
    0.06
    mania
    0.06
    updated
    0.06
    kre
    0.06
    egment
    0.06
    บาท
    0.06
    Act Density 0.000%

    No Known Activations