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

    Neuronpedia

    INDEX
    Explanations

    Software installation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .enc
    -0.07
    Pod
    -0.07
     Feet
    -0.07
     slu
    -0.07
     гер
    -0.06
     Ukrain
    -0.06
     มหาว
    -0.06
     Quarter
    -0.06
     moons
    -0.06
     뉴
    -0.06
    POSITIVE LOGITS
    Если
    0.07
     така
    0.06
     انتخاب
    0.06
     ceny
    0.06
    .DELETE
    0.06
    Sorry
    0.06
    Filed
    0.06
    Strict
    0.06
    注意
    0.06
    unistd
    0.05
    Act Density 0.035%

    No Known Activations