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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Greater
    -0.08
     существует
    -0.07
    سور
    -0.07
     lia
    -0.07
    事实上
    -0.07
     TimeUnit
    -0.07
    网格
    -0.07
     curry
    -0.07
    .flush
    -0.07
     respects
    -0.07
    POSITIVE LOGITS
    عزل
    0.08
    מבוג
    0.07
    主要用于
    0.07
    oyo
    0.07
    _idle
    0.06
    ulong
    0.06
    adc
    0.06
    ackson
    0.06
     intoxic
    0.06
     Unicorn
    0.06
    Act Density 0.002%

    No Known Activations