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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    بيان
    -0.07
     ^.
    -0.07
     حين
    -0.07
    力学
    -0.07
     También
    -0.07
     Cout
    -0.06
     lectures
    -0.06
    -bound
    -0.06
    华东
    -0.06
    炎
    -0.06
    POSITIVE LOGITS
     הגוף
    0.08
    区块
    0.06
     risen
    0.06
    没关系
    0.06
    MySQL
    0.06
     Oral
    0.06
    Regressor
    0.06
    _push
    0.06
    =$(
    0.06
    𨱔
    0.06
    Act Density 0.081%

    No Known Activations