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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     alike
    -0.08
    瑰
    -0.07
    ổ
    -0.07
    指甲
    -0.07
    經歷
    -0.07
    é
    -0.07
    英镑
    -0.07
    刪除
    -0.07
     wore
    -0.07
     AUDIO
    -0.07
    POSITIVE LOGITS
     imposed
    0.07
    一个问题
    0.07
    `s
    0.07
     OO
    0.07
     "','"
    0.07
    itrust
    0.07
    んでいる
    0.06
    냔
    0.06
    *X
    0.06
    stantiate
    0.06
    Act Density 0.003%

    No Known Activations