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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    神经网络
    0.43
    arger
    0.42
     filamentous
    0.39
     echocardi
    0.37
     камера
    0.36
     zeggen
    0.36
    健康
    0.36
     pousser
    0.35
     kämp
    0.34
     milliam
    0.34
    POSITIVE LOGITS
    etic
    0.46
     initial
    0.46
    onym
    0.46
     inicial
    0.42
    initial
    0.40
    最初の
    0.40
    magic
    0.40
     初期
    0.39
     முன்ப
    0.39
     Initial
    0.39
    Act Density 0.004%

    No Known Activations