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

    Neuronpedia

    INDEX
    Explanations

    require

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    amarin
    -0.06
     propTypes
    -0.06
     difer
    -0.06
     Tubes
    -0.06
     credible
    -0.06
     rims
    -0.06
    particle
    -0.06
     manipulated
    -0.06
     Needle
    -0.06
     éxito
    -0.06
    POSITIVE LOGITS
    ('/')[
    0.06
    Concrete
    0.06
    inery
    0.06
    راف
    0.06
    acks
    0.06
    #af
    0.06
     pek
    0.06
    [src
    0.06
    мот
    0.06
    чна
    0.06
    Act Density 0.036%

    No Known Activations