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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "close" and related concepts

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

    following "close"

    np_acts-logits-general · gemini-2.0-flash

    proximity and relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -0.62
    splan
    -0.58
    IsMutable
    -0.58
    󠁿
    -0.57
    sprogramm
    -0.57
    πω
    -0.55
     clearest
    -0.54
    spreis
    -0.54
     Baillargeon
    -0.54
    __":
    -0.54
    POSITIVE LOGITS
     knit
    0.87
     proximity
    0.84
    knit
    0.83
     quarters
    0.81
    Knit
    0.69
     Knit
    0.67
     Quarters
    0.66
     approximation
    0.66
     shave
    0.66
     knitted
    0.61
    Act Density 0.101%

    No Known Activations