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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    $txt
    -0.07
     pediatric
    -0.07
    	attr
    -0.07
     at
    -0.07
    𝓮
    -0.07
    เข
    -0.07
    信访
    -0.07
     pé
    -0.07
    �
    -0.07
     dé
    -0.07
    POSITIVE LOGITS
    masters
    0.08
     Personen
    0.08
     prueba
    0.07
    ysics
    0.07
     Nguy
    0.07
    鲈
    0.07
    0.07
    TRUE
    0.07
    -feedback
    0.07
     Hãy
    0.07
    Act Density 0.002%

    No Known Activations