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

    Neuronpedia

    INDEX
    Explanations

    Machine Learning Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     voegen
    -0.09
    	Add
    -0.08
    Adds
    -0.08
     geometry
    -0.08
    kep
    -0.08
     Elli
    -0.08
    宮
    -0.08
    romycin
    -0.08
     lossen
    -0.08
     eenvoud
    -0.08
    POSITIVE LOGITS
    .cuda
    0.13
    .set
    0.13
    _cuda
    0.12
     CUDA
    0.12
    CUDA
    0.11
    .backends
    0.11
    .get
    0.11
    (torch
    0.10
    _device
    0.10
    =torch
    0.10
    Act Density 0.007%

    No Known Activations