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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Budd
    -0.07
    nam
    -0.07
     finalized
    -0.07
     ============================================================================↵
    -0.07
    มา
    -0.07
     Freddie
    -0.07
    -new
    -0.07
    économie
    -0.07
     speaks
    -0.07
    teborg
    -0.07
    POSITIVE LOGITS
    办事处
    0.07
    /oct
    0.07
    .legend
    0.06
    _AC
    0.06
    _FLAG
    0.06
     денеж
    0.06
    -ab
    0.06
    沮丧
    0.06
    👞
    0.06
    捆绑
    0.06
    Act Density 0.004%

    No Known Activations