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

    Neuronpedia

    INDEX
    Explanations

    instances of personal references and specific structure in text

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

    x-ray generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.70
    AndEndTag
    -0.69
     estekak
    -0.61
     '\\;'
    -0.60
     архивлан
    -0.60
    elemField
    -0.56
    AutoresizingMask
    -0.56
     Wikimedijinoj
    -0.54
     BorderSide
    -0.52
     Vernunft
    -0.52
    POSITIVE LOGITS
     Terraria
    0.62
     Audiodateien
    0.32
    jsonPath
    0.32
     ق
    0.31
     לע
    0.31
     بالأ
    0.31
     Wherever
    0.30
    jsonArray
    0.30
     station
    0.29
    Appender
    0.29
    Act Density 0.001%

    No Known Activations