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

    Neuronpedia

    INDEX
    Explanations

    special characters and formatting symbols in the text

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

    mathematical notation and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    scriptcase
    -0.60
     незавершена
    -0.57
    存于互联网档案馆
    -0.57
     հղումներ
    -0.56
    تقاوى
    -0.56
    httphttps
    -0.55
     viſ
    -0.55
    AndroidJUnit
    -0.54
     AssemblyTitle
    -0.54
     ivelany
    -0.52
    POSITIVE LOGITS
     pizarra
    0.47
    '_
    0.46
     lo
    0.45
     nello
    0.43
     sullo
    0.43
     hinweg
    0.43
    openhague
    0.43
     منها
    0.43
     בין
    0.42
    _
    0.42
    Act Density 0.001%

    No Known Activations