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

    Neuronpedia

    INDEX
    Explanations

    labels and tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inding
    0.40
     وآ
    0.39
    憫
    0.39
    сний
    0.38
     выз
    0.38
     പ്രതി
    0.38
     illusions
    0.38
    徊
    0.38
     demonstration
    0.37
     रिक्
    0.37
    POSITIVE LOGITS
     labels
    2.00
    标签
    1.94
     label
    1.93
     tags
    1.74
     Labels
    1.73
    labels
    1.71
     etiquetas
    1.65
     labeling
    1.63
     Label
    1.62
     tag
    1.60
    Act Density 0.061%

    No Known Activations