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

    Neuronpedia

    INDEX
    Explanations

    specific tags or markers in structured document formats, such as HTML or LaTeX

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

    HTML tag closing `>`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.92
    tagHelperRunner
    -0.84
    MigrationBuilder
    -0.82
    SourceChecksum
    -0.81
     EClass
    -0.77
     typelib
    -0.77
    ConstraintMaker
    -0.75
    enderror
    -0.72
     GoogleFonts
    -0.70
    AxisAlignment
    -0.69
    POSITIVE LOGITS
    <td>
    0.84
      
    0.51
     
    0.43
    <blockquote>
    0.40
    <b>
    0.39
    <em>
    0.37
     the
    0.37
    Verified
    0.37
    <strong>
    0.37
    :
    0.36
    Act Density 0.001%

    No Known Activations