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

    Neuronpedia

    INDEX
    Explanations

    ref

    np_max-act · gemini-2.0-flash

    This neuron detects XML/DocBook tag markers—particularly the “ref” element names (i.e. the `<ref>` and `</ref>` tags).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ไว
    -0.07
    (block
    -0.07
     Cluster
    -0.06
     redundant
    -0.06
     Wang
    -0.06
     Як
    -0.06
    iado
    -0.06
     polymer
    -0.06
    _EXISTS
    -0.06
    orro
    -0.06
    POSITIVE LOGITS
    ezi
    0.07
    Further
    0.06
     мот
    0.06
     Increases
    0.06
     propelled
    0.06
     العم
    0.06
    @Column
    0.06
    etro
    0.06
     своє
    0.06
     kabil
    0.06
    Act Density 0.002%

    No Known Activations