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

    Neuronpedia

    INDEX
    Explanations

    successful

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    你的
    -0.07
    erten
    -0.07
    的时候
    -0.07
     immigrant
    -0.07
     Ад
    -0.07
     wakeup
    -0.07
    erno
    -0.07
    inne
    -0.06
    ROLLER
    -0.06
     beden
    -0.06
    POSITIVE LOGITS
    kategori
    0.06
     dam
    0.06
    _selection
    0.06
     testimonials
    0.06
    ดน
    0.06
    ==-
    0.06
    stk
    0.05
     丶
    0.05
    因此
    0.05
     opsiyon
    0.05
    Act Density 0.011%

    No Known Activations