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

    Neuronpedia

    INDEX
    Explanations

    Kerr

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     budget
    -0.08
     diğer
    -0.07
    综合实力
    -0.07
    .Loader
    -0.07
     użytkow
    -0.07
     myriad
    -0.07
    acky
    -0.07
    .Sc
    -0.07
    Elite
    -0.07
    (sizeof
    -0.07
    POSITIVE LOGITS
     alarm
    0.08
    kes
    0.07
     bookings
    0.07
    涟
    0.07
     restr
    0.06
     recomm
    0.06
     negligence
    0.06
    logged
    0.06
    rę
    0.06
    ارات
    0.06
    Act Density 0.000%

    No Known Activations