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

    Neuronpedia

    INDEX
    Explanations

    words or phrases indicating functionality or usage in different contexts

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

    "as" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    used as / serves as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ագրություններ
    -0.68
    脚注の使い方
    -0.47
     GenerationType
    -0.45
     gehört
    -0.44
    OGND
    -0.43
    NameInMap
    -0.43
    Населення
    -0.42
     comuniques
    -0.41
     bezit
    -0.41
    StructEnd
    -0.40
    POSITIVE LOGITS
     substitute
    0.61
     buffer
    0.61
     weapon
    0.60
    efty
    0.60
    CrossRef
    0.60
    casm
    0.59
    Means
    0.59
     Goldstein
    0.58
    Бахар
    0.58
     inspiration
    0.58
    Act Density 0.248%

    No Known Activations