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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    า
    1.03
    Require
    0.96
    вут
    0.94
    mw
    0.93
     ومرحبا
    0.91
    mv
    0.90
    a
    0.90
    กัน
    0.90
     harmonique
    0.89
     ናቸው
    0.86
    POSITIVE LOGITS
    čenja
    1.17
     Осо
    1.15
    ancement
    1.11
    ྟ
    1.08
    ฝ่าย
    1.08
     Ende
    1.05
    adores
    1.02
    orderEntry
    1.01
    人の
    1.01
     zato
    0.99
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.