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

    Neuronpedia

    INDEX
    Explanations

    instances of variable naming conventions, especially related to case sensitivity

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

    Capitalization, uppercase, or small caps

    np_acts-logits-general · gemini-2.0-flash

    capitalization markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ตร
    -0.42
    onTap
    -0.41
     asiática
    -0.41
     DESCRIPT
    -0.40
    expired
    -0.40
    ἶ
    -0.40
     bambou
    -0.39
    Сюжет
    -0.39
     externa
    -0.39
    describe
    -0.39
    POSITIVE LOGITS
     capitalization
    1.12
     capitalized
    1.12
     capital
    1.09
     capitalize
    1.03
     capitals
    1.00
     lowercase
    0.99
     uppercase
    0.98
    capital
    0.96
     Capital
    0.96
    Capital
    0.95
    Act Density 0.168%

    No Known Activations