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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting cues within the text

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

    starts with punctuation then capital

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.63
    webElementXpaths
    -0.62
    aarrggbb
    -0.57
    Élet
    -0.55
    reactstrap
    -0.53
     transfieras
    -0.52
    جغرافيا
    -0.51
     ब्रेकडाउन
    -0.50
    httphttps
    -0.49
     desgracia
    -0.49
    POSITIVE LOGITS
    transQ
    0.48
    Diweddarwch
    0.46
     capital
    0.38
     kapital
    0.36
     centrales
    0.34
     capitales
    0.34
     planter
    0.33
     kasarigan
    0.33
    XmlRootElement
    0.33
     Consumer
    0.32
    Act Density 0.006%

    No Known Activations