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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and periods, suggesting it is focused on identifying sentence boundaries

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

    programming language keywords and methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.45
    european
    -0.42
     Italijani
    -0.42
     isEqualToString
    -0.40
     Shogun
    -0.40
    optarg
    -0.39
    onedDateTime
    -0.39
     Arque
    -0.39
     Crystals
    -0.38
     BoxFit
    -0.38
    POSITIVE LOGITS
    CppMethod
    0.40
    antası
    0.39
     ***!
    0.38
    BeginContext
    0.38
    sizeCache
    0.38
    expandindo
    0.37
     getItemCount
    0.37
     largest
    0.36
     size
    0.36
    SceneManagement
    0.35
    Act Density 0.075%

    No Known Activations