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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    сон
    -0.08
    新冠
    -0.07
    née
    -0.07
    一事
    -0.07
    EdgeInsets
    -0.07
     unn
    -0.07
    ጨ
    -0.07
     benefit
    -0.07
    _USERNAME
    -0.07
    thesize
    -0.07
    POSITIVE LOGITS
    铁路
    0.07
    JECT
    0.07
     payday
    0.06
    Lines
    0.06
    SIM
    0.06
    hy
    0.06
     đã
    0.06
    tracks
    0.06
    饭菜
    0.06
     Lob
    0.06
    Act Density 0.051%

    No Known Activations