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

    Neuronpedia

    INDEX
    Explanations

    some

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (regex
    -0.07
    识
    -0.07
    ='-
    -0.07
    _ss
    -0.07
    ונג
    -0.07
     örg
    -0.06
    _ALERT
    -0.06
     Та
    -0.06
    ron
    -0.06
    _corr
    -0.06
    POSITIVE LOGITS
     sevent
    0.07
    Bulletin
    0.07
     IDirect
    0.07
    INA
    0.07
     SERVICE
    0.07
    Ubuntu
    0.07
     voluntarily
    0.07
     inherit
    0.07
    北京市
    0.06
     fibers
    0.06
    Act Density 0.038%

    No Known Activations