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

    Neuronpedia

    INDEX
    Explanations

    vector database/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .insets
    -0.09
     swing
    -0.08
     constitutional
    -0.08
     Bathroom
    -0.08
     bathroom
    -0.08
    .printf
    -0.08
     Cullen
    -0.08
     Macedonia
    -0.08
     reunited
    -0.08
     protég
    -0.08
    POSITIVE LOGITS
     storing
    0.11
    GPU
    0.09
     GPU
    0.09
    Tensor
    0.09
    .pkl
    0.09
    டியோ
    0.09
    .npy
    0.09
    (torch
    0.09
     хранения
    0.09
    _tensor
    0.09
    Act Density 0.002%

    No Known Activations