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

    Neuronpedia

    INDEX
    Explanations

    references to protective coverings or barriers, particularly masks

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

    protective masks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tui
    -0.40
     GV
    -0.39
    onel
    -0.39
     Chon
    -0.39
    ↑↑
    -0.38
    setCellValue
    -0.38
    ↠
    -0.37
    iA
    -0.36
    timi
    -0.35
    iwa
    -0.35
    POSITIVE LOGITS
     mask
    2.28
     Mask
    2.16
     masks
    2.05
    Mask
    2.00
     MASK
    1.98
     Masks
    1.95
    mask
    1.95
    Masks
    1.80
    masks
    1.70
     máscara
    1.67
    Act Density 0.005%

    No Known Activations