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

    Neuronpedia

    INDEX
    Explanations

    forms of the word "done" or expressions indicating completion or resolution

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

    task completion or end of period

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    audrait
    -0.39
    esgue
    -0.33
     Liechtenstein
    -0.33
    lightbox
    -0.33
    siąż
    -0.32
     pocz
    -0.32
    paksa
    -0.31
     太郎
    -0.30
    lesen
    -0.30
     essenciais
    -0.30
    POSITIVE LOGITS
     done
    0.88
    contentLoaded
    0.83
     DONE
    0.78
    новниш
    0.77
     Done
    0.73
     finished
    0.73
     Finished
    0.70
    TagMode
    0.69
    DONE
    0.69
    Done
    0.68
    Act Density 0.061%

    No Known Activations