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

    Neuronpedia

    INDEX
    Explanations

    references

    np_max-act · gemini-2.0-flash

    This neuron detects in-text scholarly citation markers (e.g., reference tags like [@…] and numbered bibliographic references).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .dtd
    -0.08
    ConnectionFactory
    -0.06
    最后
    -0.06
     satellites
    -0.06
    _rr
    -0.06
    npj
    -0.06
     ();
↵
    -0.06
     initComponents
    -0.06
    ('\\
    -0.06
     regain
    -0.06
    POSITIVE LOGITS
     Meth
    0.07
    INDOW
    0.07
    lington
    0.06
    الية
    0.06
     Dropbox
    0.06
     nướng
    0.06
    Fall
    0.06
    /upload
    0.06
     Watson
    0.06
     конферен
    0.06
    Act Density 0.086%

    No Known Activations