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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    er
    1.19
     गुना
    1.06
    li
    1.00
     Konz
    0.97
    ชั่น
    0.97
    in
    0.96
    ার
    0.95
     चांग
    0.94
    ли
    0.92
     volt
    0.92
    POSITIVE LOGITS
    呃
    1.35
     রাইফ
    1.32
    sodium
    1.29
     xét
    1.28
     vandalism
    1.25
    看
    1.22
     nailing
    1.22
     windmills
    1.21
    没
    1.20
    错过
    1.20
    Act Density 0.000%

    No Known Activations