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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    شاء
    -0.07
    极品
    -0.07
    pués
    -0.07
    basic
    -0.07
     experiência
    -0.07
     honorary
    -0.07
     giver
    -0.07
    隔热
    -0.06
    ienda
    -0.06
    ző
    -0.06
    POSITIVE LOGITS
    (',',$
    0.08
    ncpy
    0.07
    	cnt
    0.07
     predomin
    0.07
     ATL
    0.07
    >{$
    0.07
     כול
    0.07
    ="$
    0.07
    劼
    0.07
     nx
    0.06
    Act Density 0.013%

    No Known Activations