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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     peuvent
    -0.91
    訁
    -0.90
     americanos
    -0.90
     brasile
    -0.89
     많은
    -0.89
     recevez
    -0.88
     american
    -0.88
    AUX
    -0.87
    コットン
    -0.86
    玫
    -0.84
    POSITIVE LOGITS
    Martes
    0.88
    则
    0.84
    LiveData
    0.84
     urusan
    0.82
     secolo
    0.82
     estudiantes
    0.80
     excuses
    0.80
     ホイール
    0.79
    ですか
    0.79
     plans
    0.79
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.