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

    Neuronpedia

    INDEX
    Explanations

    hyphen

    np_max-act · gemini-2.0-flash

    The neuron specializes in spotting bibliographic citation patterns and numeric reference markers (e.g. volume, page, year sequences).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    routine
    -0.06
     FOX
    -0.06
     region
    -0.06
     zi
    -0.06
    REAL
    -0.06
    .css
    -0.06
     kz
    -0.06
     ESP
    -0.06
    ient
    -0.06
    Chi
    -0.06
    POSITIVE LOGITS
    iciary
    0.07
    ニニニニ
    0.07
     розповід
    0.06
     literary
    0.06
    pově
    0.06
    -lived
    0.06
     свидетель
    0.06
    _RESERVED
    0.06
     Hardware
    0.06
     plank
    0.06
    Act Density 0.004%

    No Known Activations