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

    Neuronpedia

    INDEX
    Explanations

    instances of code syntax and structure in programming language expressions

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

    code syntax and mathematical notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ={`
    -0.40
     window
    -0.39
    window
    -0.35
     Halliday
    -0.35
    znego
    -0.34
     car
    -0.33
    iser
    -0.33
    싶
    -0.33
     Lem
    -0.33
     SEG
    -0.33
    POSITIVE LOGITS
     <=",
    0.70
    featureID
    0.65
     esternos
    0.58
    AnchorStyles
    0.53
    ViewFeatures
    0.52
    mybatisplus
    0.52
    StructEnd
    0.51
    parsedMessage
    0.49
     виправивши
    0.49
    abstractmethod
    0.49
    Act Density 0.037%

    No Known Activations