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

    Neuronpedia

    INDEX
    Explanations

    Game scores/timers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     repetitions
    -0.07
     doubling
    -0.07
     данной
    -0.07
    Rep
    -0.07
    _Dec
    -0.07
     Lei
    -0.07
     Enable
    -0.07
    第一位
    -0.07
     bieten
    -0.07
     deserve
    -0.07
    POSITIVE LOGITS
    uth
    0.07
     Jacqu
    0.07
     псих
    0.07
     Taylor
    0.07
     Nicar
    0.07
     Orth
    0.07
    ight
    0.06
    �
    0.06
     shaft
    0.06
    结
    0.06
    Act Density 0.068%

    No Known Activations