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

    Neuronpedia

    INDEX
    Explanations

    bridge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    िक
    -0.09
     संस्क
    -0.08
    \Models
    -0.07
     preprocess
    -0.07
    icient
    -0.07
    incip
    -0.07
     בינ
    -0.07
     यांनी
    -0.07
     among
    -0.07
     participant
    -0.07
    POSITIVE LOGITS
     спокойно
    0.08
     جميل
    0.07
     enlist
    0.07
     начин
    0.07
    дя
    0.07
    _plural
    0.07
     stolz
    0.07
     دستور
    0.07
     дороги
    0.07
    ATR
    0.07
    Act Density 0.006%

    No Known Activations