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

    Neuronpedia

    INDEX
    Explanations

    referee

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    蹀
    -0.07
    쏘
    -0.07
    フォ
    -0.07
     Fond
    -0.07
     bào
    -0.07
    opy
    -0.07
     cd
    -0.07
     Boulevard
    -0.07
     xsi
    -0.07
     pardon
    -0.07
    POSITIVE LOGITS
    随即
    0.06
    Ͳ
    0.06
    .Route
    0.06
     fick
    0.06
    	mc
    0.06
    顺利
    0.06
     العسكري
    0.06
    _interrupt
    0.06
    _com
    0.06
     بحيث
    0.06
    Act Density 0.002%

    No Known Activations