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

    Neuronpedia

    INDEX
    Explanations

    code syntax

    np_max-act · gemini-2.0-flash

    segments of code or content that involve importing libraries or modules, along with defined structures for managing or operating on those imports.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on decimal numeric literals (floating-point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     alleged
    -0.07
    롱
    -0.06
    istan
    -0.06
    ّد
    -0.06
     rhetoric
    -0.06
    Large
    -0.06
    Pages
    -0.06
    &page
    -0.06
     erotisk
    -0.05
    SCAN
    -0.05
    POSITIVE LOGITS
    Remember
    0.08
    قال
    0.07
     },{
    0.07
     elim
    0.06
    _DP
    0.06
    атель
    0.06
     …↵
    0.06
    adio
    0.06
    知识
    0.06
     العربي
    0.06
    Act Density 0.028%

    No Known Activations