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

    Neuronpedia

    INDEX
    Explanations

    Lasso method

    np_max-act · gemini-2.0-flash

    sentences related to regression analysis, particularly in high-dimensional contexts.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on words naming or referring to regularization penalty terms (especially L1/“lasso”), their parameters (e.g. λ), and related shrinkage terminology.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    asu
    -0.07
    Gram
    -0.07
    passed
    -0.07
    нять
    -0.07
     languages
    -0.07
     +-
    -0.06
    -success
    -0.06
    urt
    -0.06
    нуть
    -0.06
     McKay
    -0.06
    POSITIVE LOGITS
     Dim
    0.07
    _fixed
    0.07
     Phi
    0.07
    (Model
    0.06
     sesso
    0.06
     CMD
    0.06
    HomeController
    0.06
     professionals
    0.06
    _arg
    0.06
     jewellery
    0.06
    Act Density 0.006%

    No Known Activations