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

    Neuronpedia

    INDEX
    Explanations

    excitation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    엔
    -0.08
    Š
    -0.07
    俶
    -0.06
    	events
    -0.06
     Fans
    -0.06
    组
    -0.06
    氛
    -0.06
    小店
    -0.06
    ights
    -0.06
    yet
    -0.06
    POSITIVE LOGITS
     republican
    0.08
    erate
    0.08
     최
    0.08
    칙
    0.07
    .DateField
    0.07
    ובי
    0.07
    רכים
    0.07
    (inflater
    0.07
    actionDate
    0.07
    DECL
    0.07
    Act Density 0.005%

    No Known Activations