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

    Neuronpedia

    INDEX
    Explanations

    repetition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ##_
    -0.07
     مز
    -0.07
     Phelps
    -0.06
     спортив
    -0.06
     SOCIAL
    -0.06
    าศาสตร
    -0.06
    {}_
    -0.06
     Rental
    -0.06
    徒歩
    -0.06
    (xx
    -0.06
    POSITIVE LOGITS
    outlined
    0.07
     info
    0.07
     respectively
    0.06
     других
    0.06
    Coefficient
    0.06
    іла
    0.06
     fadeIn
    0.06
    Synopsis
    0.06
     insulting
    0.06
     repeatedly
    0.06
    Act Density 0.005%

    No Known Activations