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

    Neuronpedia

    INDEX
    Explanations

    ernet

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ブル
    -0.07
    rea
    -0.07
    Ж
    -0.06
    Mid
    -0.06
     Lilly
    -0.06
    егодня
    -0.06
    Ten
    -0.06
     guten
    -0.06
    West
    -0.06
    ADMIN
    -0.06
    POSITIVE LOGITS
     absent
    0.07
    objc
    0.06
    amaha
    0.06
     nil
    0.06
    rstrip
    0.06
     defaultManager
    0.06
     DependencyProperty
    0.06
     فعالیت
    0.06
     optarg
    0.06
     seeker
    0.06
    Act Density 0.005%

    No Known Activations