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

    Neuronpedia

    INDEX
    Explanations

    push

    np_max-act · gemini-2.0-flash

    The neuron detects commands in Git workflows—particularly high‐level imperative verbs like merge, push, pull, reset, and rebase.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    LEM
    -0.07
    과
    -0.06
    šší
    -0.06
    บค
    -0.06
     hits
    -0.06
     Saunders
    -0.06
    silver
    -0.06
     indir
    -0.06
    tex
    -0.06
    _helpers
    -0.06
    POSITIVE LOGITS
     mouseClicked
    0.07
    .Promise
    0.07
    push
    0.07
    、何
    0.07
    .QRect
    0.06
    ควร
    0.06
    نع
    0.06
     ****************************************************************************
    0.06
    .wikipedia
    0.06
    勢
    0.06
    Act Density 0.001%

    No Known Activations