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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "the" and phrases related to reviewing or examining content

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

    the record

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ècie
    -0.59
    Билгалдахарш
    -0.56
     betweenstory
    -0.56
    XtraReports
    -0.56
    OGND
    -0.53
    AddTagHelper
    -0.53
    fjspx
    -0.53
     للاسماء
    -0.52
    tagHelperRunner
    -0.51
    awtextra
    -0.51
    POSITIVE LOGITS
     kandungan
    0.51
    ambién
    0.43
     dokumenta
    0.43
     pleadings
    0.42
     statistics
    0.42
     photographs
    0.41
     orina
    0.41
     documents
    0.40
     lisse
    0.40
     waveforms
    0.40
    Act Density 0.037%

    No Known Activations