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

    Neuronpedia

    INDEX
    Explanations

    direct access or execution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ли
    0.53
    ">+</
    0.49
    Drug
    0.45
     getImage
    0.45
     chemist
    0.44
     recite
    0.44
    相
    0.43
    Lake
    0.43
    াণ্ড
    0.43
    Advent
    0.42
    POSITIVE LOGITS
    łączy
    0.45
     गट
    0.45
     mastect
    0.45
    économ
    0.44
    ไม่ต้อง
    0.43
    땜
    0.43
     réfé
    0.43
     معظم
    0.43
     reclaiming
    0.42
     نجم
    0.42
    Act Density 0.001%

    No Known Activations