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

    Neuronpedia

    INDEX
    Explanations

    Exponents and the number 2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Welfare
    -0.07
     dairy
    -0.07
     изб
    -0.07
    Sugar
    -0.07
     Sussex
    -0.06
    Annotations
    -0.06
     tracking
    -0.06
     makers
    -0.06
     spraying
    -0.06
    ugar
    -0.06
    POSITIVE LOGITS
     ül
    0.07
     bliss
    0.06
    خوان
    0.06
    原
    0.06
    店
    0.06
    �
    0.06
    .HtmlControls
    0.06
    abama
    0.06
    ทำ
    0.06
    맛
    0.06
    Act Density 0.011%

    No Known Activations