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

    Neuronpedia

    INDEX
    Explanations

    EDC knives and scripting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    الس
    0.57
    疼痛
    0.53
    ئ
    0.53
    ็
    0.52
    だけでなく
    0.51
    ）（
    0.51
    מור
    0.51
    鎗
    0.50
    佂
    0.50
    स
    0.50
    POSITIVE LOGITS
     EDC
    0.59
     skyscrapers
    0.57
     skyscraper
    0.57
     alternator
    0.57
     Kipling
    0.57
     stabilize
    0.56
     bandana
    0.56
     Compaq
    0.56
     Claire
    0.54
     flaps
    0.54
    Act Density 0.011%

    No Known Activations