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

    Neuronpedia

    INDEX
    Explanations

    pieces of code and code-related discussions

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

    code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.42
     average
    -0.39
     Pascual
    -0.37
     favorite
    -0.36
     maioria
    -0.35
    dataclass
    -0.34
     nạ
    -0.34
     Nacionales
    -0.34
    DOCTYPE
    -0.34
     pergunt
    -0.33
    POSITIVE LOGITS
     setCode
    0.77
    code
    0.71
     code
    0.71
     CODE
    0.68
    Code
    0.68
    CODE
    0.67
     código
    0.65
    代码
    0.64
     Code
    0.63
     coding
    0.62
    Act Density 0.058%

    No Known Activations