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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing the concept of "best possible" or optimal outcomes

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

    extreme outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cools
    -0.42
     bruja
    -0.41
     acceptez
    -0.40
     svårt
    -0.39
     antigüedad
    -0.39
     dueño
    -0.39
     brasileño
    -0.37
     agresión
    -0.37
    utilisons
    -0.36
     cualquiera
    -0.36
    POSITIVE LOGITS
     poffible
    0.58
    UnusedPrivate
    0.57
     المعيارى
    0.56
     queſta
    0.55
    ۜ
    0.54
     ſte
    0.54
    ⤹
    0.53
    IRQn
    0.51
    pcm
    0.51
     пожалуйста
    0.51
    Act Density 0.013%

    No Known Activations