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

    Neuronpedia

    INDEX
    Explanations

    phrases or keywords related to understanding or comprehension

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

    understand what or how

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bounty
    -0.41
    latLng
    -0.38
     Dishes
    -0.37
     epics
    -0.37
    ListPage
    -0.37
     poultry
    -0.36
     Poultry
    -0.36
     dishes
    -0.35
     Sero
    -0.35
     liệt
    -0.35
    POSITIVE LOGITS
     Understanding
    1.17
     understand
    1.16
     Understand
    1.15
    Understanding
    1.14
     understanding
    1.14
    understand
    1.13
     understands
    1.12
    understanding
    1.11
    Understand
    1.09
     comprendre
    0.93
    Act Density 0.033%

    No Known Activations