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

    Neuronpedia

    INDEX
    Explanations

    Proliferation and growth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Carol
    -0.06
    ो,
    -0.06
     rebound
    -0.06
     pul
    -0.06
     });↵↵
    -0.06
     Razor
    -0.06
    رت
    -0.06
    یل
    -0.06
     Nico
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     Became
    0.07
    우리
    0.07
     hư
    0.07
     recieved
    0.07
     Denn
    0.06
     Navy
    0.06
     Volunteer
    0.06
     Оп
    0.06
     sentencing
    0.06
     deserving
    0.06
    Act Density 0.013%

    No Known Activations