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

    Neuronpedia

    INDEX
    Explanations

    HTML tags and navigation elements

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

    html list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.51
     smtplib
    -0.44
    帖最后由
    -0.44
    MENAFN
    -0.43
    LÄ
    -0.43
    athione
    -0.42
     Slider
    -0.42
     Hathaway
    -0.42
    matchCondition
    -0.41
    Бахар
    -0.41
    POSITIVE LOGITS
     للمعارف
    0.62
    0.62
     pertama
    0.54
     Económica
    0.54
     doméstico
    0.53
     primeiro
    0.51
     primeira
    0.50
     zuerst
    0.50
     primero
    0.50
     marinho
    0.49
    Act Density 0.011%

    No Known Activations