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

    Neuronpedia

    INDEX
    Explanations

    Machine learning interpretability

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is find mentions of model interpretability and explainability in AI/ML contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    桥
    -0.07
     acı
    -0.06
     [{"
    -0.06
     jos
    -0.06
    kud
    -0.06
    oke
    -0.06
     setDefaultCloseOperation
    -0.06
     pageSize
    -0.06
    nesia
    -0.06
     registrations
    -0.06
    POSITIVE LOGITS
     showcase
    0.06
     introduced
    0.06
    物理
    0.06
    漫画
    0.06
     amidst
    0.06
     حالة
    0.06
    کاری
    0.06
     différents
    0.06
     reasoning
    0.06
    ‌کنند
    0.06
    Act Density 0.004%

    No Known Activations