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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mozilla
    -0.07
    hole
    -0.06
    rates
    -0.06
     penetr
    -0.06
    .weight
    -0.06
    élé
    -0.06
    .Usage
    -0.06
    .client
    -0.06
    des
    -0.06
    'label
    -0.06
    POSITIVE LOGITS
     Bölüm
    0.07
     UserRole
    0.06
    (Map
    0.06
     Supplementary
    0.06
    Feb
    0.06
     GI
    0.06
     🙂
    0.06
    跨
    0.06
     fazla
    0.06
    ху
    0.06
    Act Density 0.067%

    No Known Activations