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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to medical conditions and their treatment methodologies

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

    anti-cancer therapy, human fat, only decay

    np_acts-logits-general · gemini-2.5-flash-lite

    It detects the infinitival "to" (and similar short function words marking purpose/relations like "for").

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    吹
    -0.32
     Erbe
    -0.32
      
    -0.28
     here
    -0.28
     parte
    -0.25
    mi
    -0.25
    ípio
    -0.25
    lnie
    -0.25
     hier
    -0.25
    yyj
    -0.25
    POSITIVE LOGITS
    WriteTagHelper
    0.96
    تقاوى
    0.81
    0.78
    ロウィン
    0.76
    ContentAsync
    0.76
    ########.
    0.76
     gyhoeddwyd
    0.75
    IsContent
    0.75
     ***!
    0.75
    0.74
    Act Density 0.098%

    No Known Activations