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

    Neuronpedia

    INDEX
    Explanations

    structured data types and their properties in code

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

    The token "type" followed by certain punctuation

    np_acts-logits-general · gemini-2.0-flash

    type designation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tikang
    -0.50
    󠁴
    -0.39
     Partici
    -0.36
    Географи
    -0.34
    RenderAtEndOf
    -0.34
     titoli
    -0.34
     dichiarato
    -0.34
    LEncoder
    -0.33
     voegen
    -0.33
    iſen
    -0.33
    POSITIVE LOGITS
     disambiguazione
    0.54
    type
    0.52
     category
    0.48
    sourceType
    0.48
    twimg
    0.46
     type
    0.46
     userType
    0.44
    viewType
    0.44
    setType
    0.43
     Италијани
    0.43
    Act Density 0.558%

    No Known Activations