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

    Neuronpedia

    INDEX
    Explanations

    line

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <|end_header_id|>
    -0.07
     Franç
    -0.07
    Compar
    -0.07
    front
    -0.07
     Ara
    -0.07
    -loop
    -0.06
     FOX
    -0.06
    ุญ
    -0.06
     apple
    -0.06
     vast
    -0.06
    POSITIVE LOGITS
     цього
    0.07
     �
    0.07
    setState
    0.07
     Certified
    0.06
    _DEAD
    0.06
     alıp
    0.06
    ğimiz
    0.06
    password
    0.06
     cele
    0.06
     �
    0.06
    Act Density 0.001%

    No Known Activations