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

    Neuronpedia

    INDEX
    Explanations

    text that relates to highlighted or emphasized elements in documents

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

    highlighting and underlining text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    VersionUID
    -0.55
    蚪
    -0.54
    RegistryLite
    -0.52
    
    -0.50
     jdbcTemplate
    -0.43
    LayoutPanel
    -0.40
    encoj
    -0.40
     Púb
    -0.39
    Referencer
    -0.39
    DatabaseError
    -0.39
    POSITIVE LOGITS
     highlighted
    0.73
     highlighting
    0.67
     Highlight
    0.66
    highlighted
    0.66
    highlight
    0.64
     highlight
    0.61
     underlined
    0.58
     underline
    0.58
    Highlight
    0.58
    Highlighted
    0.56
    Act Density 0.184%

    No Known Activations