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

    Neuronpedia

    INDEX
    Explanations

    connections and transitions within the text, particularly related to mentions or numerical data

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

    Follows commas in descriptive clauses

    np_acts-logits-general · gemini-2.0-flash

    commas and phrases like "for example"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     colspan
    -0.47
    UIC
    -0.43
    出版年
    -0.42
    AndEndTag
    -0.42
    BMS
    -0.41
    Explicación
    -0.41
    Portail
    -0.41
    lios
    -0.40
     Pende
    -0.40
    InjectAttribute
    -0.39
    POSITIVE LOGITS
     Италијани
    0.52
    تقاوى
    0.48
     ***!
    0.47
    ="@+
    0.47
    makeConstraints
    0.45
     EconPapers
    0.45
     otomatig
    0.43
    dibly
    0.43
    ruik
    0.42
    FailureListener
    0.42
    Act Density 0.599%

    No Known Activations