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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     нада
    -0.06
    Chr
    -0.06
     yaptığı
    -0.06
    ']").
    -0.06
    _fact
    -0.06
    ierce
    -0.06
    なが
    -0.06
    وزيع
    -0.06
    зація
    -0.05
     unfolding
    -0.05
    POSITIVE LOGITS
    �
    0.07
     MARK
    0.07
     流
    0.07
     retailers
    0.07
    _^(
    0.06
     according
    0.06
     repost
    0.06
     shrimp
    0.06
    rowsers
    0.06
     ジャ
    0.06
    Act Density 0.005%

    No Known Activations