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

    Neuronpedia

    INDEX
    Explanations

    book chapters

    np_max-act · gemini-2.0-flash

    This neuron activates on section‐heading markers (e.g., “Scene 1:”, “Act II:”, “Chapter 3:”) indicating numbered divisions in the script.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     expend
    -0.07
    -0.07
     Margaret
    -0.07
     scriptures
    -0.07
     briefly
    -0.07
     time
    -0.07
     sys
    -0.07
    -0.07
    .tencent
    -0.07
     Fred
    -0.07
    POSITIVE LOGITS
     краї
    0.07
    �
    0.07
     sitesinde
    0.07
     Να
    0.07
    ном
    0.06
    ْم
    0.06
    ้าพ
    0.06
    кой
    0.06
    ฤ
    0.06
    _MORE
    0.06
    Act Density 0.022%

    No Known Activations