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

    Neuronpedia

    INDEX
    Explanations

    technical terms and elements within programming and coding contexts

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

    Code or markup snippets

    np_acts-logits-general · gemini-2.0-flash

    citations and code elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </strong>
    -0.72
    .
    -0.68
     $\
    -0.63
     
    -0.62
    ↵↵
    -0.62
     O
    -0.61
    ,
    -0.60
    '
    -0.60
    <strong>
    -0.60
    <unused63>
    -0.59
    POSITIVE LOGITS
     betweenstory
    1.77
    parsedMessage
    1.58
     tartalomajánló
    1.56
    aarrggbb
    1.54
     ExecuteAsync
    1.45
    AddTagHelper
    1.41
    ########.
    1.39
     '\\;'
    1.34
    ItemBackground
    1.33
    RenderAtEndOf
    1.33
    Act Density 1.698%

    No Known Activations