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

    Neuronpedia

    INDEX
    Explanations

    described

    np_max-act · gemini-2.0-flash

    This neuron fires most strongly on the common function words and reporting verbs that structure scientific‐abstract sentences (e.g. “The…are described,” “using,” “by,” “are,” “described”), effectively detecting the phrasing of academic biological study descriptions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _FLASH
    -0.07
     सबस
    -0.06
     bouts
    -0.06
    وجه
    -0.06
     hayat
    -0.06
    الك
    -0.06
     OLD
    -0.06
    迹
    -0.06
     nuis
    -0.06
     cancell
    -0.06
    POSITIVE LOGITS
    �
    0.07
    ↵      ↵
    0.06
     gratuits
    0.06
     Qual
    0.06
    Cong
    0.06
    toLocale
    0.06
     Explorer
    0.06
    (ray
    0.06
    -publish
    0.06
     qualité
    0.06
    Act Density 0.044%

    No Known Activations