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

    Neuronpedia

    INDEX
    Explanations

    sudden exclamations or replies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     variables
    0.45
     prerequisites
    0.40
     biocompat
    0.39
     ecosystems
    0.38
     biomarkers
    0.38
     bibliographic
    0.38
     correlations
    0.37
     habitats
    0.37
     firmware
    0.36
     ergonomic
    0.36
    POSITIVE LOGITS
     Suddenly
    0.50
     suddenly
    0.48
     replied
    0.48
    Suddenly
    0.47
    这时
    0.46
     gasped
    0.45
     replying
    0.42
     groaned
    0.41
     exclaimed
    0.41
     thereupon
    0.41
    Act Density 0.011%

    No Known Activations