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

    Neuronpedia

    INDEX
    Explanations

    non-english text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -series
    -0.08
    _width
    -0.07
     adjusted
    -0.07
     Torrent
    -0.07
    FromFile
    -0.07
    _Space
    -0.07
    与
    -0.07
     можно
    -0.06
     Matrix
    -0.06
     undergoing
    -0.06
    POSITIVE LOGITS
     referrals
    0.06
    fails
    0.06
     junto
    0.06
    oop
    0.06
     校
    0.05
     ACTIONS
    0.05
    ῦ
    0.05
     }}">↵
    0.05
     HIM
    0.05
    imedia
    0.05
    Act Density 0.011%

    No Known Activations