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

    Neuronpedia

    INDEX
    Explanations

    hospital length of stay

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    连忙
    -0.07
    .SetBool
    -0.07
    ổ
    -0.07
     ت
    -0.07
    פס
    -0.07
     Ezek
    -0.07
     handles
    -0.07
    _cs
    -0.07
     rollout
    -0.06
    發展
    -0.06
    POSITIVE LOGITS
     المر
    0.08
     stal
    0.08
     Дмитр
    0.07
     Anal
    0.07
    ugin
    0.07
    [,]
    0.07
     JWT
    0.07
     Byrne
    0.07
    UMAN
    0.06
    硿
    0.06
    Act Density 0.017%

    No Known Activations