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

    Neuronpedia

    INDEX
    Explanations

    Computer code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Amendments
    -0.07
     employees
    -0.07
    沚
    -0.07
    𬭁
    -0.07
    三年
    -0.07
     Airlines
    -0.07
    _bulk
    -0.07
     만들어
    -0.07
     kaufen
    -0.07
     Invoice
    -0.07
    POSITIVE LOGITS
    솜
    0.07
    Я
    0.07
     removed
    0.07
    束
    0.07
    Short
    0.06
    STRACT
    0.06
     он
    0.06
     оч
    0.06
    适当的
    0.06
    ![
    0.06
    Act Density 0.000%

    No Known Activations