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

    Neuronpedia

    INDEX
    Explanations

    Colonial and "ial"

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “colonial.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Streams
    -0.07
     �
    -0.07
     spacing
    -0.07
     Avery
    -0.07
     unst
    -0.06
     unre
    -0.06
    скільки
    -0.06
     �
    -0.06
     ************************************************
    -0.06
    ωτερ
    -0.06
    POSITIVE LOGITS
     colonial
    0.11
     Colonial
    0.10
     colonization
    0.08
     Colony
    0.08
     Colonel
    0.08
     Oliver
    0.07
    房
    0.07
    çı
    0.07
     colony
    0.07
     colonies
    0.07
    Act Density 0.006%

    No Known Activations