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

    Neuronpedia

    INDEX
    Explanations

    code installation and generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ш
    0.59
     whenever
    0.56
     originates
    0.56
     dies
    0.55
     constamment
    0.55
     enforces
    0.55
     కర్
    0.54
     verhindert
    0.54
     transmitter
    0.54
     -
    0.53
    POSITIVE LOGITS
    tidyverse
    0.93
     microbiome
    0.80
    dplyr
    0.77
    投资
    0.70
    下一步
    0.67
    vegan
    0.67
    éments
    0.65
    WorkingDirectory
    0.65
     проєкту
    0.65
    ypter
    0.65
    Act Density 0.392%

    No Known Activations