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

    Neuronpedia

    INDEX
    Explanations

    medical studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     respect
    -0.07
     العرب
    -0.06
     interstate
    -0.06
     đạt
    -0.06
     Cyc
    -0.06
     kdo
    -0.06
     spawned
    -0.06
    ‌شده
    -0.06
     آب
    -0.06
    POSITIVE LOGITS
    "},↵
    0.07
    础
    0.06
     Luckily
    0.06
     Κό
    0.06
    Luckily
    0.06
    (expected
    0.06
    Ultimately
    0.06
     Interrupt
    0.06
    ITS
    0.06
    (errorMessage
    0.06
    Act Density 0.071%

    No Known Activations