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

    Neuronpedia

    INDEX
    Explanations

    AI legal filings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ération
    0.27
     arousal
    0.27
    rogens
    0.26
    aabb
    0.26
    糇
    0.26
    ോഷ്യ
    0.26
     voila
    0.26
     όμως
    0.26
     ¼
    0.25
    ópez
    0.25
    POSITIVE LOGITS
    на
    0.37
    ки
    0.35
    ة
    0.35
    ری
    0.33
    ла
    0.33
    it
    0.33
    त
    0.33
    ка
    0.32
    ل
    0.32
    ся
    0.32
    Act Density 0.018%

    No Known Activations