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

    Neuronpedia

    INDEX
    Explanations

    attributes

    np_max-act · gemini-2.0-flash

    This neuron activates on demonstrative references and generic placeholders, especially words like “These” (e.g. “These things,” “These factors”) that point to previously mentioned items.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    άρχ
    -0.06
     radix
    -0.06
    	light
    -0.06
     hacked
    -0.06
     memes
    -0.06
     entreprise
    -0.06
     breve
    -0.06
    Cars
    -0.06
    十一
    -0.06
     foods
    -0.06
    POSITIVE LOGITS
    pal
    0.07
    refer
    0.06
    _IC
    0.06
    】↵
    0.06
    ummy
    0.06
    ’s
    0.06
    coach
    0.06
    odigo
    0.06
     συ
    0.06
    па
    0.06
    Act Density 0.129%

    No Known Activations