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

    Neuronpedia

    INDEX
    Explanations

    patterns involving underscores and related placeholders or syntax elements in code

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

    only VALID IX FL TEXT

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <>",
    -0.54
    最快更新
    -0.52
     snippetHide
    -0.52
    InjectAttribute
    -0.52
     cherchés
    -0.52
    ंदीखरीदारी
    -0.50
    MigrationBuilder
    -0.50
    AnchorStyles
    -0.50
    BeginInit
    -0.49
    awtextra
    -0.49
    POSITIVE LOGITS
    kuuta
    0.42
    haraan
    0.40
    日まで
    0.39
     ouvrages
    0.39
    colades
    0.38
    semb
    0.38
     attain
    0.38
     avenge
    0.38
     يتيمه
    0.37
    strophy
    0.37
    Act Density 0.123%

    No Known Activations