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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    觕
    1.00
    除此之外
    0.99
    㱛
    0.97
    連携
    0.97
     succinctly
    0.96
    یف
    0.96
    ក្នុង
    0.96
    kve
    0.93
    ﺖ
    0.92
    呦
    0.91
    POSITIVE LOGITS
    .
    1.70
    )
    1.64
     a
    1.53
    ),
    1.50
    ,
    1.47
     the
    1.33
    ).
    1.29
    ור
    1.29
    ers
    1.28
    ।
    1.27
    Act Density 0.000%

    No Known Activations