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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate comprehension or knowledge of a subject

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

    "understand"

    np_acts-logits-general · gemini-2.0-flash

    understand meaning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelper
    -0.66
    jupiter
    -0.63
    тари
    -0.61
    ot
    -0.53
    番
    -0.53
    glBindTexture
    -0.51
    toggler
    -0.51
     vela
    -0.51
    datagrid
    -0.50
    NOTIFY
    -0.49
    POSITIVE LOGITS
     Understand
    1.32
    understand
    1.27
    Understand
    1.25
     understands
    1.17
     understand
    1.14
    understood
    1.12
     understanding
    1.10
     understandings
    1.10
    understanding
    1.06
     understood
    1.05
    Act Density 0.082%

    No Known Activations