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

    Neuronpedia

    INDEX
    Explanations

    library

    np_max-act · gemini-2.0-flash

    This neuron fires on code lines that load or reference R packages (e.g. library()/require() calls and package names like ggplot2).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Partition
    -0.08
     take
    -0.07
     Voc
    -0.07
    .Save
    -0.07
     Latin
    -0.07
     partition
    -0.07
    asu
    -0.07
     scans
    -0.07
    ку
    -0.07
    dept
    -0.06
    POSITIVE LOGITS
    elden
    0.07
     nombreux
    0.07
    ไลน
    0.06
    .R
    0.06
     експ
    0.06
    tee
    0.06
    史
    0.06
     перемен
    0.06
    compass
    0.06
     utilizar
    0.06
    Act Density 0.002%

    No Known Activations