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

    Neuronpedia

    INDEX
    Explanations

    Mill

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Set
    -0.08
     Career
    -0.07
    )return
    -0.07
    .ValidationError
    -0.07
    恋人
    -0.07
    下面
    -0.07
    .Vector
    -0.07
     contin
    -0.07
     aspiring
    -0.07
    🐐
    -0.07
    POSITIVE LOGITS
    ありが
    0.07
     Mill
    0.07
     اللي
    0.07
    沘
    0.07
    딜
    0.07
     installed
    0.06
     cümle
    0.06
     thỏ
    0.06
     cinco
    0.06
    払
    0.06
    Act Density 0.010%

    No Known Activations