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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     skyscr
    -0.08
     اتحاد
    -0.08
    联盟
    -0.08
    stairs
    -0.08
     متحد
    -0.08
     联
    -0.07
     physic
    -0.07
     கூட்ட
    -0.07
     Gift
    -0.07
     Sachs
    -0.07
    POSITIVE LOGITS
     判断
    0.12
     판단
    0.11
    判断
    0.11
    Classification
    0.10
     classified
    0.10
     classify
    0.10
     categorized
    0.10
    Classifier
    0.10
     classifiers
    0.09
    分類
    0.09
    Act Density 0.018%

    No Known Activations