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

    Neuronpedia

    INDEX
    Explanations

    Programming languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     possession
    -0.08
    .slice
    -0.07
    訳
    -0.07
     repetitions
    -0.07
     BLUE
    -0.07
     خدمات
    -0.06
    ATTLE
    -0.06
     เมษายน
    -0.06
     Spaces
    -0.06
     Generating
    -0.06
    POSITIVE LOGITS
    384
    0.06
    _low
    0.06
    当然
    0.06
     мне
    0.06
    =").
    0.06
     Optional
    0.06
     Tiffany
    0.06
    .nextToken
    0.06
    .decorate
    0.06
    ально
    0.06
    Act Density 0.007%

    No Known Activations