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

    Neuronpedia

    INDEX
    Explanations

    summaries and extracts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Booking
    -0.07
    booking
    -0.06
     якого
    -0.06
    ongyang
    -0.06
     command
    -0.06
    ря
    -0.06
    Forms
    -0.06
    acho
    -0.06
    kowski
    -0.06
     dough
    -0.06
    POSITIVE LOGITS
    :ｉ
    0.06
    NSUserDefaults
    0.06
    PagerAdapter
    0.06
    iciente
    0.06
     Numero
    0.06
     chrono
    0.06
     서로
    0.06
    폰
    0.06
    acic
    0.06
     Sterling
    0.06
    Act Density 0.002%

    No Known Activations