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

    Neuronpedia

    INDEX
    Explanations

    bra

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sunset
    -0.08
     Imaging
    -0.07
    _IO
    -0.07
     khuyến
    -0.07
     Đối
    -0.07
     Turn
    -0.06
    �
    -0.06
    (models
    -0.06
    (w
    -0.06
     Văn
    -0.06
    POSITIVE LOGITS
     bra
    0.11
     bras
    0.07
     Bra
    0.06
    -random
    0.06
     gradient
    0.06
     jou
    0.06
    ,)↵
    0.06
    itelné
    0.06
    NDER
    0.06
     stavu
    0.06
    Act Density 0.003%

    No Known Activations