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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    مناسب
    -0.07
    paced
    -0.07
    娑
    -0.07
     Funny
    -0.07
     pewnością
    -0.07
    ưng
    -0.07
     Printed
    -0.07
     rapp
    -0.07
     Blessed
    -0.06
    蓠
    -0.06
    POSITIVE LOGITS
     admin
    0.07
    _fk
    0.07
     wichtig
    0.07
     Iter
    0.07
     featured
    0.07
    UGE
    0.06
    串
    0.06
    貅
    0.06
     dav
    0.06
     feature
    0.06
    Act Density 0.005%

    No Known Activations