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

    Neuronpedia

    INDEX
    Explanations

    Bibliography

    np_max-act · gemini-2.0-flash

    The neuron is primarily activated by bibliography-style headings and reference entries (e.g. “Bibliography,” “Checklist,” “Filmography,” “Index,” and similar citation tokens).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Sch
    -0.06
    Blueprint
    -0.06
     vítěz
    -0.06
     rehearsal
    -0.06
     luder
    -0.06
    forming
    -0.06
     Elim
    -0.06
     فنی
    -0.06
     buddy
    -0.06
    овый
    -0.06
    POSITIVE LOGITS
    kr
    0.07
    _AUT
    0.07
     _|
    0.07
     '..',
    0.07
    uter
    0.07
     γ
    0.06
    อก
    0.06
    gili
    0.06
     >↵↵
    0.06
    ylene
    0.06
    Act Density 0.012%

    No Known Activations