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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal proceedings and courtroom dialogue

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

    Punctuation, like apostrophes and colons

    np_acts-logits-general · gemini-2.0-flash

    questions or dialogue starts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Bronnen
    -0.67
    "),
    -0.60
    TagMode
    -0.59
    IntoConstraints
    -0.57
    ("-");
    -0.56
    ”…
    -0.54
    ='';
    -0.54
     ‘
    -0.53
     “
    -0.52
     abt
    -0.52
    POSITIVE LOGITS
    Ladies
    0.69
     ویکی‌پدیای
    0.67
     Gentlemen
    0.65
    Excuse
    0.64
    Today
    0.62
    Gentlemen
    0.60
    EndContext
    0.59
     Ladies
    0.58
     Excuse
    0.58
     Seeder
    0.56
    Act Density 0.236%

    No Known Activations