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

    Neuronpedia

    INDEX
    Explanations

    linear algebra over GF(2)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lev
    -0.09
    AE
    -0.08
    ae
    -0.08
     pounds
    -0.08
     caring
    -0.08
     lip
    -0.08
    Lev
    -0.08
     mitochondrial
    -0.08
     unilateral
    -0.08
     pasión
    -0.08
    POSITIVE LOGITS
     broadcast
    0.09
     weerstand
    0.09
     Broadcast
    0.09
     Probability
    0.09
     dictators
    0.09
     augmente
    0.08
     الوحدة
    0.08
     Enumer
    0.08
    	field
    0.08
     Drupal
    0.08
    Act Density 0.008%

    No Known Activations