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

    Neuronpedia

    INDEX
    Explanations

    single digit numbers

    np_max-act · gemini-2.0-flash

    The neuron detects citation metadata—especially year and page-number fragments in parenthetical APA-style references.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Del
    -0.07
     pile
    -0.07
     Clintons
    -0.06
    镜
    -0.06
    蒙
    -0.06
     clan
    -0.06
    charg
    -0.06
    таки
    -0.06
     ім
    -0.06
     categoryId
    -0.06
    POSITIVE LOGITS
    рогра
    0.06
     regular
    0.06
     Fork
    0.06
     orgán
    0.06
     Hà
    0.06
     propose
    0.06
     devuelve
    0.06
     Burma
    0.06
    ॉर
    0.06
     fitted
    0.06
    Act Density 0.014%

    No Known Activations