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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating different categories, types, or classifications

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

    both

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.51
    RenderAtEndOf
    -0.35
     certain
    -0.34
     bruit
    -0.34
    üf
    -0.34
     Alembic
    -0.32
     certaine
    -0.32
    神
    -0.32
    ❉
    -0.31
     rospy
    -0.31
    POSITIVE LOGITS
    Both
    0.78
     beide
    0.77
     båda
    0.74
     Beide
    0.71
     beider
    0.70
     both
    0.69
     begge
    0.68
     berdua
    0.68
     Both
    0.68
     entrambi
    0.67
    Act Density 0.092%

    No Known Activations