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

    Neuronpedia

    INDEX
    Explanations

    code and numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     paddingTop
    -0.07
     nextProps
    -0.06
     cityName
    -0.06
    ustom
    -0.06
    uppercase
    -0.06
     outputPath
    -0.06
    าส
    -0.06
     člov
    -0.06
     нев
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     Hybrid
    0.08
    فاع
    0.06
     physically
    0.06
     fully
    0.06
     "\(
    0.06
     hybrid
    0.06
    Universal
    0.06
    速度
    0.06
     Heavy
    0.06
    0.06
    Act Density 0.002%

    No Known Activations