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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, especially names and titles

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

    Japanese names like Nakatani

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.52
    AddTagHelper
    -0.46
    MigrationBuilder
    -0.43
     виправивши
    -0.43
    RenderAtEndOf
    -0.43
    -0.42
    twimg
    -0.42
     StatelessWidget
    -0.42
    essentiel
    -0.41
     שוליים
    -0.41
    POSITIVE LOGITS
     Pandit
    0.51
     smtplib
    0.51
    nador
    0.49
     Noyes
    0.47
    下手
    0.46
    Preliminary
    0.45
     Rendez
    0.44
    outputFile
    0.44
     prelimin
    0.44
     Alexey
    0.44
    Act Density 0.185%

    No Known Activations