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

    Neuronpedia

    INDEX
    Explanations

    District

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (embed
    -0.06
     �
    -0.06
     Orb
    -0.06
    ,arr
    -0.06
    angles
    -0.06
    ้ร
    -0.06
     Sax
    -0.06
     uniqu
    -0.06
     Mob
    -0.06
     vet
    -0.06
    POSITIVE LOGITS
     sağlıklı
    0.07
     cherish
    0.07
     diren
    0.07
    mensaje
    0.06
     thinking
    0.06
    unj
    0.06
     dotenv
    0.06
    esan
    0.06
    (ARG
    0.06
     sqlalchemy
    0.06
    Act Density 0.001%

    No Known Activations