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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     cambio
    -0.08
    셍
    -0.07
    gunakan
    -0.07
    叙利亚
    -0.07
    חם
    -0.07
    .t
    -0.07
    icho
    -0.07
    離れ
    -0.06
     придется
    -0.06
    ꦲ
    -0.06
    POSITIVE LOGITS
    ()<<
    0.06
    ()>
    0.06
     DECLARE
    0.06
    委宣传
    0.06
     pay
    0.06
     дост
    0.06
    -make
    0.06
    追随
    0.06
    вез
    0.06
    더
    0.06
    Act Density 0.002%

    No Known Activations