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

    Neuronpedia

    INDEX
    Explanations

    key points related to definitions and characteristics of objects or concepts

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

    the word "key"

    np_acts-logits-general · gemini-2.0-flash

    key and keys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bord
    -0.42
    bord
    -0.41
    InitStruct
    -0.40
    альное
    -0.38
    ParallelGroup
    -0.36
    उ
    -0.36
     leksikon
    -0.36
    andaag
    -0.36
    vill
    -0.35
    花板
    -0.35
    POSITIVE LOGITS
     key
    4.02
    key
    3.61
     Key
    3.52
    Key
    3.41
     KEY
    3.08
    KEY
    2.96
     keys
    2.79
     Keys
    2.36
     Schlüssel
    2.35
     chiave
    2.29
    Act Density 0.226%

    No Known Activations