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

    Neuronpedia

    INDEX
    Explanations

    references to scheduling options and updates related to features

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

    Indicates changes or updates

    np_acts-logits-general · gemini-2.0-flash

    changes and updates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.58
    InjectAttribute
    -0.52
    jsonwebtoken
    -0.52
    Décès
    -0.51
     évent
    -0.51
     Потом
    -0.49
    ::*;
    -0.48
     рано
    -0.48
     Профиль
    -0.48
    defer
    -0.47
    POSITIVE LOGITS
     improved
    1.43
     increased
    1.33
    improved
    1.30
     changed
    1.29
    increased
    1.22
     now
    1.21
     теперь
    1.16
    新たに
    1.12
     improvements
    1.09
    Increased
    1.09
    Act Density 0.563%

    No Known Activations