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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .fe
    -0.08
    /ext
    -0.08
    润
    -0.08
     шы
    -0.08
     pyl
    -0.08
    -0.08
    Vic
    -0.08
    峰
    -0.08
    Feign
    -0.08
     mạng
    -0.08
    POSITIVE LOGITS
     �
    0.08
     nutrition
    0.07
    ...),
    0.07
    ost
    0.07
    0.07
     предпри
    0.07
     Amerika
    0.07
    スタ
    0.07
     Nutrition
    0.07
     administered
    0.07
    Act Density 0.007%
    No Known Activations