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

    Neuronpedia

    INDEX
    Explanations

    Foreign language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     redd
    -0.07
    (Location
    -0.07
     tast
    -0.06
     adolescents
    -0.06
    ,last
    -0.06
     lessen
    -0.06
    ester
    -0.06
     Tail
    -0.06
     Robbie
    -0.06
    (act
    -0.06
    POSITIVE LOGITS
     різні
    0.07
    ¶¶
    0.07
     Beginners
    0.07
    lijk
    0.07
    儿
    0.06
    pu
    0.06
     energetic
    0.06
     CDs
    0.06
     ره
    0.06
     المللی
    0.06
    Act Density 0.034%

    No Known Activations