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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tam
    -0.07
    将持续
    -0.07
     nuances
    -0.07
    _fast
    -0.06
     dolphins
    -0.06
     рублей
    -0.06
    .Insert
    -0.06
    兵
    -0.06
     января
    -0.06
     marriage
    -0.06
    POSITIVE LOGITS
    เทศกา
    0.07
    定量
    0.07
    serializer
    0.07
    cta
    0.06
     тек
    0.06
     itinerary
    0.06
     limiting
    0.06
    .Info
    0.06
    .MaximizeBox
    0.06
    builder
    0.06
    Act Density 0.037%

    No Known Activations