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

    Neuronpedia

    INDEX
    Explanations

    where is

    np_max-act · gemini-2.0-flash

    This neuron fires on Spanish transitional phrases introducing code blocks, especially the “Aquí va” sequence.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    pytest
    -0.07
     elit
    -0.07
     производства
    -0.07
    ंत
    -0.06
     PyErr
    -0.06
    (iterator
    -0.06
    apol
    -0.06
     Daha
    -0.06
    nard
    -0.06
     ตำบล
    -0.06
    POSITIVE LOGITS
     toggle
    0.06
    -->↵
    0.06
    着
    0.06
    バ
    0.06
     حداقل
    0.06
     camel
    0.06
     Bel
    0.06
     orden
    0.06
     stool
    0.06
     Donald
    0.06
    Act Density 0.006%

    No Known Activations