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

    Neuronpedia

    INDEX
    Explanations

    neural network terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     douche
    0.94
     Jewelry
    0.84
     heirloom
    0.83
     Mileage
    0.77
     oriente
    0.77
     hickory
    0.77
     королев
    0.77
     Craigslist
    0.76
    JOptionPane
    0.75
     Civic
    0.73
    POSITIVE LOGITS
     neural
    2.26
     Neural
    2.19
    Neural
    2.17
    神经网络
    2.09
     TensorFlow
    2.09
    neural
    2.08
    Tensor
    2.06
    训练
    2.06
     convolutional
    2.05
     ReLU
    1.96
    Act Density 1.474%

    No Known Activations