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

    Neuronpedia

    INDEX
    Explanations

    changes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    788
    -0.06
    ServiceProvider
    -0.06
     flock
    -0.06
    059
    -0.06
    057
    -0.06
    (TEST
    -0.06
    098
    -0.06
    .dtype
    -0.06
     disappe
    -0.06
     Iranian
    -0.06
    POSITIVE LOGITS
     ayar
    0.07
    :maj
    0.06
     виконання
    0.06
    icism
    0.06
    че
    0.06
     adaptations
    0.06
     přek
    0.06
    ){
↵
    0.06
     Stores
    0.06
     прич
    0.06
    Act Density 0.019%

    No Known Activations