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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conclusions or ultimate outcomes

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

    a final result or conclusion

    np_acts-logits-general · gemini-2.0-flash

    ultimately / eventually

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.71
    IntoConstraints
    -0.67
    Хьажоргаш
    -0.65
     للمعارف
    -0.65
     imagui
    -0.64
     ſont
    -0.63
    WebElementEntity
    -0.63
     pleaſure
    -0.63
     faſt
    -0.62
    astify
    -0.61
    POSITIVE LOGITS
     eventually
    0.76
     ultimately
    0.75
    eventually
    0.75
     eventual
    0.71
     Eventually
    0.70
     ultimate
    0.70
    Eventually
    0.69
    Ultimately
    0.69
     Ultimately
    0.68
     uiteindelijk
    0.59
    Act Density 0.208%

    No Known Activations