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

    Neuronpedia

    INDEX
    Explanations

    neural networks and coding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     enjoyable
    -0.09
    ijas
    -0.09
     copyright
    -0.08
     நடை
    -0.08
    agre
    -0.08
    agra
    -0.08
     autoridad
    -0.08
     THROW
    -0.08
     containment
    -0.08
    giore
    -0.08
    POSITIVE LOGITS
    .unsqueeze
    0.11
     embeddings
    0.10
     입력
    0.10
    _encoded
    0.09
    .inputs
    0.09
    embedding
    0.09
     predictors
    0.09
    (inputs
    0.09
    Inputs
    0.09
    .Input
    0.08
    Act Density 0.014%

    No Known Activations