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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating constancy or similarity over time

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

    remains the same or constant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Paglinawan
    -0.76
     estekak
    -0.72
    Jeografia
    -0.67
     kasarigan
    -0.64
     препратки
    -0.63
    expandindo
    -0.62
     nakalista
    -0.61
     initComponents
    -0.61
     <=",
    -0.59
     PeEnEo
    -0.58
    POSITIVE LOGITS
     unchanging
    0.56
    不变
    0.52
     changed
    0.50
    Change
    0.50
    Changed
    0.49
     Change
    0.49
     chang
    0.48
     change
    0.48
    CHANGE
    0.48
    change
    0.47
    Act Density 0.057%

    No Known Activations