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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Meksiku
    -1.14
     varandra
    -1.09
    __":
    -1.06
    NameInMap
    -1.05
     دیکھیے
    -1.01
     defaultstate
    -1.01
    دانشنامهٔ
    -1.00
     étrangère
    -0.99
    RegressionTest
    -0.96
     auffi
    -0.94
    POSITIVE LOGITS
     on
    0.54
     in
    0.54
    ↵
    0.54
    .
    0.53
    -
    0.52
    ↵↵
    0.47
    ,
    0.47
    <eos>
    0.46
     
    0.46
    </h3>
    0.45
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.