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

    Neuronpedia

    INDEX
    Explanations

    phrases related to official agencies or regulatory bodies

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

    compiled specific sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⤹
    -0.70
    RenderAtEndOf
    -0.67
     propOrder
    -0.66
    rungsseite
    -0.64
    usercontent
    -0.61
    InstrumentedTest
    -0.60
    лтамалар
    -0.60
     kaarangay
    -0.60
     nonUne
    -0.59
     Normdatei
    -0.58
    POSITIVE LOGITS
     rowspan
    0.32
     doigt
    0.31
     analogies
    0.30
    Compiled
    0.29
     globally
    0.29
     compiled
    0.28
     orel
    0.28
    tible
    0.28
     conhece
    0.28
     circonst
    0.28
    Act Density 0.018%

    No Known Activations