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

    Neuronpedia

    INDEX
    Explanations

    words that indicate the presence of negation or absence of something

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

    "Such" or "these" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    determiners followed by specific nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    itattu
    -0.44
     dép
    -0.42
     épis
    -0.39
    结
    -0.37
     تضيفلها
    -0.36
     ſta
    -0.35
     houſe
    -0.35
    Gén
    -0.35
    significant
    -0.34
    Вла
    -0.34
    POSITIVE LOGITS
    aarrggbb
    0.63
    DoubleQuotes
    0.56
    UnusedPrivate
    0.55
    adaptiveStyles
    0.52
    setupUi
    0.52
    ]")]
    0.48
    webElementXpaths
    0.48
    ↻
    0.47
    mockMvc
    0.47
    parsedMessage
    0.47
    Act Density 1.080%

    No Known Activations