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

    Neuronpedia

    INDEX
    Explanations

    Dystopian literature

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Index
    -0.07
    通過
    -0.07
     succeeded
    -0.07
    .plus
    -0.07
     multiplayer
    -0.06
    Size
    -0.06
    CKER
    -0.06
    =-=-=-=-=-=-=-=-
    -0.06
     lớn
    -0.06
    Composite
    -0.06
    POSITIVE LOGITS
     router
    0.06
    ุทธ
    0.06
     İngilizce
    0.06
    gression
    0.06
    �
    0.06
     انت
    0.06
    <|end_of_text|>
    0.06
    леч
    0.06
    <UFunction
    0.05
    рех
    0.05
    Act Density 0.008%

    No Known Activations