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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming variable naming conventions

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

    Capitalization, casing, and symbols

    np_acts-logits-general · gemini-2.0-flash

    uppercase and lowercase text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ChildIndex
    -0.54
    AddWithValue
    -0.51
    íqu
    -0.51
    Sito
    -0.51
    findpost
    -0.48
     Sito
    -0.48
     متعلقه
    -0.47
     tänka
    -0.46
     muualla
    -0.46
     estekak
    -0.46
    POSITIVE LOGITS
     capital
    1.15
     lowercase
    1.14
     capitalization
    1.08
     capitalize
    1.06
     capitalized
    1.05
     uppercase
    1.04
     capitals
    1.03
     Capital
    1.03
    Capital
    1.01
     CAPITAL
    1.00
    Act Density 0.183%

    No Known Activations