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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _SEC
    -0.09
     erratic
    -0.09
    克斯
    -0.08
    有一些
    -0.07
    bery
    -0.07
    会影响到
    -0.07
    ём
    -0.07
    mys
    -0.07
    적
    -0.07
    diğimiz
    -0.07
    POSITIVE LOGITS
    ల
    0.07
     تن
    0.07
     dispenser
    0.07
    Senate
    0.07
     obtener
    0.06
    ９
    0.06
    ﯷ
    0.06
     neighborhood
    0.06
    .Reverse
    0.06
     barrels
    0.06
    Act Density 0.000%

    No Known Activations