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

    Neuronpedia

    INDEX
    Explanations

    al

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ９
    -0.07
    _irq
    -0.07
     IntPtr
    -0.07
    ませ
    -0.07
    มาจาก
    -0.07
     lengths
    -0.06
     emerged
    -0.06
    圳
    -0.06
    ******/↵
    -0.06
     wax
    -0.06
    POSITIVE LOGITS
    роб
    0.08
    Atual
    0.07
    言语
    0.07
    ង
    0.07
    자동
    0.07
    jab
    0.06
     Appl
    0.06
    奏
    0.06
    Class
    0.06
     ostat
    0.06
    Act Density 0.003%

    No Known Activations