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

    Neuronpedia

    INDEX
    Explanations

    machine learning code/documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Templates
    -0.08
     넘
    -0.08
    systems
    -0.08
     containers
    -0.08
    _templates
    -0.07
     boto
    -0.07
     sọ
    -0.07
     Criterion
    -0.07
     Hosts
    -0.07
    Criterion
    -0.07
    POSITIVE LOGITS
     hopefully
    0.11
    hopefully
    0.10
     bagus
    0.09
     спустя
    0.09
    效果
    0.09
     получилось
    0.08
     approaching
    0.08
     લગભગ
    0.08
    徐
    0.08
     pleasing
    0.08
    Act Density 0.011%

    No Known Activations