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

    Neuronpedia

    INDEX
    Explanations

    Request

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    brief
    -0.07
     XXX
    -0.07
    bracht
    -0.07
    病毒
    -0.06
     enthusiastically
    -0.06
    摇头
    -0.06
    ısı
    -0.06
     SIN
    -0.06
     meds
    -0.06
    蜢
    -0.06
    POSITIVE LOGITS
     scraper
    0.08
    铫
    0.07
    ឋ
    0.07
     Kash
    0.07
    نتائ
    0.07
    עור
    0.07
     Sequence
    0.07
     dóla
    0.06
    ليف
    0.06
     Flow
    0.06
    Act Density 0.003%

    No Known Activations