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

    Neuronpedia

    INDEX
    Explanations

    pg

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ocomplete
    -0.08
     поколения
    -0.08
     разработки
    -0.08
    avorable
    -0.07
     всего
    -0.07
     hora
    -0.07
     hig
    -0.07
    GEST
    -0.07
     പല
    -0.07
    ಉ
    -0.07
    POSITIVE LOGITS
     Bluff
    0.07
     healthy
    0.07
     tru
    0.07
     coffees
    0.07
     alm
    0.07
     Mustang
    0.07
     blonde
    0.07
     Murray
    0.07
     পড়
    0.06
     Amazing
    0.06
    Act Density 0.003%

    No Known Activations