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

    Neuronpedia

    INDEX
    Explanations

    all, most

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PyQt
    -0.07
     prestigious
    -0.06
    ，本
    -0.06
    -0.06
     ghi
    -0.06
     бор
    -0.06
    Was
    -0.06
    uyla
    -0.06
    -Y
    -0.06
    yc
    -0.06
    POSITIVE LOGITS
    vanished
    0.07
     programma
    0.07
     crackers
    0.06
     znam
    0.06
    -lasting
    0.06
    !!!
    0.06
    Choice
    0.06
     giống
    0.06
     incons
    0.06
    离开
    0.06
    Act Density 0.007%

    No Known Activations