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

    Neuronpedia

    INDEX
    Explanations

    будет

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Far
    -0.07
    861
    -0.07
     hj
    -0.07
    ätze
    -0.07
     Friedman
    -0.07
     manipulation
    -0.07
    Entry
    -0.07
     जे
    -0.06
    Far
    -0.06
     harms
    -0.06
    POSITIVE LOGITS
     связано
    0.09
    /is
    0.09
     выгляд
    0.09
     нашим
    0.08
     запр
    0.08
     विन
    0.08
     частью
    0.08
     иметь
    0.08
     synonymous
    0.08
     لدينا
    0.08
    Act Density 0.012%

    No Known Activations