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

    Neuronpedia

    INDEX
    Explanations

    PG

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     XXX
    -0.07
     SUN
    -0.07
     congressman
    -0.06
     LAT
    -0.06
     dessert
    -0.06
    (Auth
    -0.06
    _processor
    -0.06
     embarrassment
    -0.06
    丝路
    -0.06
     discern
    -0.06
    POSITIVE LOGITS
    冁
    0.08
     pornofilm
    0.07
    	UInt
    0.07
     phê
    0.07
    갑
    0.07
     игр
    0.07
    .amazon
    0.07
    也有很多
    0.07
    홑
    0.07
     kep
    0.07
    Act Density 0.004%

    No Known Activations