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

    Neuronpedia

    INDEX
    Explanations

    Pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <|endoftext|>
    -0.13
    <|reserved_200016|>
    -0.13
    <|reserved_200004|>
    -0.09
    �
    -0.07
     "
    -0.07
     Cher
    -0.07
     Brass
    -0.07
    :
    -0.06
     &
    -0.06
    -0.06
    POSITIVE LOGITS
     وضع
    0.09
     다양한
    0.09
     مثلا
    0.09
     įvair
    0.09
     استخ
    0.08
     eingesetzt
    0.08
     κάτι
    0.08
     انواع
    0.08
    在线视频
    0.08
     durchführen
    0.08
    Act Density 0.839%

    No Known Activations