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

    Neuronpedia

    INDEX
    Explanations

    accidentally created, To demonstrate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    릴
    0.48
     alkaloids
    0.46
     auspices
    0.44
     Prong
    0.44
    胧
    0.44
     Hound
    0.42
     oiseaux
    0.42
    ตั้ง
    0.42
    ங்கிய
    0.42
    hok
    0.42
    POSITIVE LOGITS
     speculated
    0.48
     polémica
    0.46
     mistrust
    0.45
     procl
    0.45
    ᱽ
    0.45
     preferable
    0.44
     braced
    0.43
     recycled
    0.43
     distrust
    0.42
     responded
    0.41
    Act Density 0.001%

    No Known Activations