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

    Neuronpedia

    INDEX
    Explanations

    Period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Chew
    -0.08
    苫
    -0.07
    RIX
    -0.07
     Darth
    -0.07
    包子
    -0.07
    日在
    -0.07
     emphasis
    -0.07
    ליק
    -0.07
    挈
    -0.07
    范畴
    -0.07
    POSITIVE LOGITS
     aqu
    0.07
     fetched
    0.07
     fishing
    0.07
    连接
    0.06
    Schema
    0.06
     anatomy
    0.06
    уш
    0.06
    脖子
    0.06
    _p
    0.06
     ещ
    0.06
    Act Density 0.001%

    No Known Activations