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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash

    This neuron activates on bibliographic and reference entries (e.g., book and article titles, publication details) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     toolkit
    -0.07
     McCorm
    -0.07
     Німеч
    -0.06
    KeyId
    -0.06
    ritz
    -0.06
     在
    -0.06
    �
    -0.06
    _different
    -0.06
    .*)
    -0.06
    firebase
    -0.06
    POSITIVE LOGITS
    -ip
    0.07
    ути
    0.07
     spolup
    0.07
    ออกแบบ
    0.06
     hlavně
    0.06
     nech
    0.06
     能
    0.06
    ESSAGES
    0.06
    視
    0.06
    ³
    0.06
    Act Density 0.025%

    No Known Activations