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

    Neuronpedia

    INDEX
    Explanations

    Never saying no

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ↓
    -0.07
     bonds
    -0.07
    	com
    -0.06
    -di
    -0.06
    .springboot
    -0.06
     aio
    -0.06
    Assignable
    -0.06
     réuss
    -0.06
    这种
    -0.06
    (si
    -0.06
    POSITIVE LOGITS
      ↵↵
    0.07
    尼亚
    0.06
    -driving
    0.06
    weeted
    0.06
    VIN
    0.06
     Kate
    0.06
    ality
    0.06
    /gallery
    0.06
    丁
    0.06
    عام
    0.06
    Act Density 0.003%

    No Known Activations