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

    Neuronpedia

    INDEX
    Explanations

    R code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Dried
    0.39
     дія
    0.39
     কমে
    0.38
    σί
    0.37
     diminution
    0.36
     Jewellery
    0.35
     HUOBI
    0.35
    βο
    0.35
     เยอะ
    0.35
    鋆
    0.35
    POSITIVE LOGITS
    setwd
    0.92
     library
    0.87
    library
    0.80
     cat
    0.75
    cat
    0.74
    ```{
    0.71
     Library
    0.69
     ggplot
    0.67
     libraries
    0.66
     Cat
    0.64
    Act Density 0.014%

    No Known Activations