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

    Neuronpedia

    INDEX
    Explanations

    references to manual or handcrafted processes

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

    manual action or creation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.62
     ویکی‌پدی
    -0.52
     архивлан
    -0.48
    httphttps
    -0.47
    Демографія
    -0.45
    WebVitals
    -0.44
     nanti
    -0.44
    rawDesc
    -0.43
    webElementXpaths
    -0.43
     Accesorios
    -0.42
    POSITIVE LOGITS
     hand
    0.60
    Hand
    0.52
     handwritten
    0.51
     Hand
    0.51
    hand
    0.50
     manually
    0.46
     اليد
    0.44
    MessageOf
    0.43
     handmade
    0.43
     HAND
    0.42
    Act Density 0.075%

    No Known Activations