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

    Neuronpedia

    INDEX
    Explanations

    function call syntax in code snippets

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

    code blocks and language constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.86
    migrationBuilder
    -0.83
    WriteTagHelper
    -0.78
    ########.
    -0.66
     wikipagina
    -0.66
    zzleHttp
    -0.65
    StandardCharsets
    -0.65
    Hentet
    -0.63
    EndInit
    -0.63
    RegressionTest
    -0.63
    POSITIVE LOGITS
     pré
    0.33
     “
    0.33
    <h1>
    0.32
    ⓧ
    0.31
    「
    0.29
     model
    0.29
     continuous
    0.28
    underbrace
    0.28
     הי
    0.28
     Ministro
    0.28
    Act Density 0.038%

    No Known Activations