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

    Neuronpedia

    INDEX
    Explanations

    pytorch

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    蚬
    0.56
    顾问
    0.53
     ईमित्र
    0.53
    乾燥
    0.51
    configFile
    0.51
     آمریک
    0.49
    ورية
    0.49
    Beverungen
    0.48
     méthodique
    0.48
    貉
    0.48
    POSITIVE LOGITS
     torch
    2.02
    torch
    1.72
     Torch
    1.56
    Torch
    1.55
     tensor
    1.52
     tensors
    1.51
     torches
    1.43
    Tensor
    1.37
    pytorch
    1.31
     Tensor
    1.27
    Act Density 0.135%

    No Known Activations