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

    Neuronpedia

    INDEX
    Explanations

    programming-related syntax and constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    run or running commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     löyty
    -0.35
     navideña
    -0.35
     navideñas
    -0.35
    ându
    -0.33
     keş
    -0.32
     дописавши
    -0.31
     löytyy
    -0.31
     Schluss
    -0.31
     jamás
    -0.30
     enemmän
    -0.30
    POSITIVE LOGITS
     Running
    1.39
     Run
    1.37
     run
    1.36
     RUN
    1.35
     Runs
    1.34
    Running
    1.32
    Run
    1.32
    running
    1.30
     running
    1.30
     RUNNING
    1.28
    Act Density 0.018%

    No Known Activations