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

    Neuronpedia

    INDEX
    Explanations

    mask

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Rach
    0.77
    瑟
    0.73
     बुद्ध
    0.73
     SQLite
    0.72
    Database
    0.70
     जितेंद्र
    0.69
     Schen
    0.69
    ัพ
    0.69
     विराजमान
    0.68
     Rails
    0.68
    POSITIVE LOGITS
     mask
    4.24
     masks
    4.09
    Mask
    3.93
     Mask
    3.90
     Masks
    3.77
    mask
    3.73
    masks
    3.43
     masker
    3.30
    マスク
    3.30
     masking
    3.21
    Act Density 0.103%

    No Known Activations