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

    Neuronpedia

    INDEX
    Explanations

    software coding standards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     distortion
    -0.07
     amis
    -0.07
     hott
    -0.07
     monstr
    -0.07
    ์โ
    -0.06
     Sh
    -0.06
    Array
    -0.06
     recalled
    -0.06
     boyunca
    -0.06
    ('$
    -0.06
    POSITIVE LOGITS
     backyard
    0.07
     تحصیل
    0.07
     知
    0.07
    ην
    0.07
    <thead
    0.06
     yem
    0.06
     이름
    0.06
    endency
    0.06
     savaş
    0.06
     (!(
    0.06
    Act Density 0.008%

    No Known Activations