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

    Neuronpedia

    INDEX
    Explanations

    structured XML or JSON data elements, including keys and values

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

    Tokens before "value"

    np_acts-logits-general · gemini-2.0-flash

    key-value data retrieval

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cintura
    -0.51
    onomía
    -0.48
     napkin
    -0.44
    قایناق‌لار
    -0.44
     solidarité
    -0.43
    HttpRequest
    -0.43
     alma
    -0.42
    FormTagHelper
    -0.42
     juger
    -0.42
     Koll
    -0.42
    POSITIVE LOGITS
     value
    1.13
    value
    0.95
     VALUE
    0.94
     Value
    0.91
    Value
    0.91
    VALUE
    0.89
     values
    0.89
     valeur
    0.85
    getValue
    0.79
    addValue
    0.76
    Act Density 0.322%

    No Known Activations