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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    lean
    -0.08
    不会有
    -0.07
    瘳
    -0.07
    やすく
    -0.07
    _head
    -0.07
    UpperCase
    -0.07
     coastline
    -0.07
     Collapse
    -0.06
    픕
    -0.06
    大多
    -0.06
    POSITIVE LOGITS
    嗤
    0.07
     contractual
    0.07
     Dutch
    0.07
    rd
    0.07
    倮
    0.07
    Fabric
    0.07
    iska
    0.07
    𝆣
    0.06
    illac
    0.06
     Expanded
    0.06
    Act Density 0.048%

    No Known Activations