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

    Neuronpedia

    INDEX
    Explanations

    Seeking advice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     register
    -0.07
     tenant
    -0.07
    (Environment
    -0.06
     RoundedRectangle
    -0.06
     Luxury
    -0.06
    ////////////////////////////////////////////////////////////////////////////
    -0.06
     Tall
    -0.06
     Kor
    -0.06
    focused
    -0.06
     criminal
    -0.06
    POSITIVE LOGITS
    าด
    0.07
    ایل
    0.07
    emme
    0.07
    덕
    0.07
     سپتامبر
    0.07
     Dec
    0.06
    venge
    0.06
     çözüm
    0.06
    FL
    0.06
     xuyên
    0.06
    Act Density 0.128%

    No Known Activations