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

    Neuronpedia

    INDEX
    Explanations

    .com

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     //~
    -0.07
    GCC
    -0.07
    、その
    -0.07
     installer
    -0.07
     Soviet
    -0.07
    その
    -0.06
    균
    -0.06
     باشند
    -0.06
    dük
    -0.06
    "));↵
    -0.06
    POSITIVE LOGITS
     Doctors
    0.06
     medicine
    0.06
     slashes
    0.06
     refund
    0.06
     celebrities
    0.06
    �
    0.06
    rome
    0.06
     Serge
    0.05
     professionals
    0.05
    meal
    0.05
    Act Density 0.001%

    No Known Activations