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

    Neuronpedia

    INDEX
    Explanations

    statistics and percentages related to different variables

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

    Percentages

    np_acts-logits-general · gemini-2.0-flash

    numerical percentages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Oye
    -0.41
    isco
    -0.41
    Attra
    -0.40
    ゴリー
    -0.38
     ͡
    -0.38
    וא
    -0.38
    marginHorizontal
    -0.37
    oge
    -0.37
    segna
    -0.37
    meteries
    -0.37
    POSITIVE LOGITS
     percent
    0.65
     Paglinawan
    0.58
     chance
    0.57
    percent
    0.55
     (%)
    0.50
     Prozent
    0.49
     (\%)
    0.49
    SharedDtor
    0.48
    Kjelder
    0.46
     $(\%)$
    0.45
    Act Density 0.307%

    No Known Activations