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

    Neuronpedia

    INDEX
    Explanations

    Condition

    np_max-act · gemini-2.0-flash

    The neuron fires on XML attribute names and their assignment syntax (e.g. the bits like Label="…" or Condition="…" in tags).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     brink
    -0.07
    Africa
    -0.06
    �
    -0.06
     Ferguson
    -0.06
     domination
    -0.06
    ّت
    -0.06
     deadlines
    -0.06
    탁
    -0.06
    .startDate
    -0.06
    料
    -0.06
    POSITIVE LOGITS
    chemas
    0.07
    Optional
    0.06
    utor
    0.06
    	Integer
    0.06
    indice
    0.06
     declares
    0.06
     chương
    0.06
    ="↵
    0.06
     uz
    0.06
     <-
    0.06
    Act Density 0.004%

    No Known Activations