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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ’.
    -1.20
    ’.”
    -1.18
    ,’”
    -1.17
    ',"
    -1.09
    '.
    -1.04
    ,’
    -1.02
    ,'"
    -1.00
     مشين
    -1.00
    RegressionTest
    -0.98
    ,'
    -0.95
    POSITIVE LOGITS
    gendes
    0.38
     bilin
    0.36
    евна
    0.36
    ритори
    0.35
    斯基
    0.35
    tettu
    0.34
     стой
    0.34
     Dummies
    0.34
     Nunn
    0.34
    SupportActionBar
    0.33
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.