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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    全体
    0.85
     mọi
    0.78
    すべての
    0.76
     Każ
    0.76
     gesamten
    0.75
    даго
    0.74
    izawa
    0.74
     Practitioners
    0.74
    лекет
    0.73
    尔
    0.72
    POSITIVE LOGITS
    think
    0.98
     poisons
    0.95
     dislikes
    0.94
     methylene
    0.91
    வின்
    0.89
     dispose
    0.88
     carbonates
    0.87
     think
    0.87
     disposal
    0.86
    nitrogen
    0.86
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.