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

    Neuronpedia

    INDEX
    Explanations

    definitions and classifications of various items or concepts

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

    a type of classification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BrowserRouter
    -0.33
     penghar
    -0.32
    上下
    -0.32
     BrowserRouter
    -0.32
     Terima
    -0.30
    prefixer
    -0.30
    askar
    -0.30
    ʧ
    -0.30
     huddled
    -0.30
    iNdEx
    -0.29
    POSITIVE LOGITS
    一種
    0.57
    一种
    0.53
    的一种
    0.52
     ujednoznacz
    0.52
    исленность
    0.51
    OutputType
    0.50
    brium
    0.49
     Waray
    0.47
     kasarigan
    0.47
     technique
    0.47
    Act Density 0.033%

    No Known Activations