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

    Neuronpedia

    INDEX
    Explanations

    building structures and enclosures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lapply
    0.59
     ataque
    0.53
    มาชิก
    0.52
     dbo
    0.49
     saját
    0.48
    َل
    0.48
     nên
    0.48
     vse
    0.48
     dáng
    0.48
     yani
    0.47
    POSITIVE LOGITS
     fences
    0.77
     প্রাচ
    0.76
     دیوار
    0.74
     walls
    0.72
     벽
    0.68
    walls
    0.67
     doors
    0.66
    doors
    0.64
     fence
    0.64
     tembok
    0.64
    Act Density 0.276%

    No Known Activations