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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating progress or the need for improvement

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

    still or yet to do/improve

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vPvB
    -0.40
    +#+#
    -0.34
    Cerca
    -0.34
    Зноскі
    -0.34
    Política
    -0.34
     fonti
    -0.33
     helmet
    -0.33
    进制
    -0.32
    bufio
    -0.32
     hansen
    -0.32
    POSITIVE LOGITS
    StoryboardSegue
    0.73
    HomeAsUpEnabled
    0.64
    Remaining
    0.57
     للاسماء
    0.54
    まだまだ
    0.53
     ainda
    0.52
     disambiguazione
    0.49
     ſtill
    0.47
    encore
    0.47
     Италијани
    0.47
    Act Density 0.019%

    No Known Activations