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

    Neuronpedia

    INDEX
    Explanations

    syntax-related elements in programming code

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

    user input delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -0.57
    TagMode
    -0.49
     colspan
    -0.49
    AutoScaleMode
    -0.45
     CURIAM
    -0.45
     ExecuteAsync
    -0.40
     disambiguazione
    -0.40
     gravedad
    -0.39
    
    -0.38
     kaca
    -0.38
    POSITIVE LOGITS
     surla
    0.44
     propOrder
    0.42
     canst
    0.41
    ihnach
    0.40
    CloseOperation
    0.40
    LabelTagHelper
    0.40
    __":
    0.40
    adeloupe
    0.40
    __':
    0.39
     rifles
    0.39
    Act Density 0.032%

    No Known Activations