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

    Neuronpedia

    INDEX
    Explanations

    key phrases related to performance and effectiveness

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

    best when, spent simply

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enfans
    -0.53
     للمعارف
    -0.46
    ArrowToggle
    -0.45
     PopupWindow
    -0.44
     mères
    -0.43
    etcode
    -0.43
    égories
    -0.43
    Anhalt
    -0.42
    ⤒
    -0.42
    LabelTagHelper
    -0.42
    POSITIVE LOGITS
     AssemblyCompany
    0.47
     للاسماء
    0.43
     Мексичка
    0.38
     carbox
    0.35
    ymas
    0.34
     cherchés
    0.34
     Biôgrafia
    0.33
     ideally
    0.33
    トリ
    0.33
     disfrut
    0.32
    Act Density 0.044%

    No Known Activations