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

    Neuronpedia

    INDEX
    Explanations

    LaTeX commands and symbols related to mathematical formatting

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

    LaTeX, code, or punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WebElementEntity
    -1.16
    parsedMessage
    -1.04
     betweenstory
    -1.03
    MessageTagHelper
    -1.00
    <unused41>
    -0.93
    <unused68>
    -0.93
    <unused17>
    -0.92
    <unused21>
    -0.92
    <unused16>
    -0.92
    <unused14>
    -0.92
    POSITIVE LOGITS
    .
    0.49
    }
    0.47
    ;
    0.42
    )
    0.40
    /
    0.38
    no
    0.36
    ri
    0.34
    era
    0.34
    am
    0.34
    U
    0.33
    Act Density 0.002%

    No Known Activations