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

    Neuronpedia

    INDEX
    Explanations

    references to all-encompassing concepts or collective actions

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

    all the time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inSlope
    -0.37
     tracking
    -0.36
    eció
    -0.36
    terase
    -0.35
     Tracking
    -0.35
    WaitGroup
    -0.33
     astore
    -0.33
    ienced
    -0.32
    ностей
    -0.32
    pun
    -0.32
    POSITIVE LOGITS
     constantly
    2.17
     constamment
    1.71
     continually
    1.68
     constantemente
    1.66
     постоянно
    1.59
     continuamente
    1.56
     continuously
    1.54
     ständig
    1.45
     CONSTANT
    1.45
     sürekli
    1.41
    Act Density 0.105%

    No Known Activations