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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ०
    1.28
    宴
    1.27
    navigationItem
    1.21
    𝘪
    1.20
    ੱਖ
    1.19
     fashionable
    1.19
    ००
    1.19
    𝘧
    1.18
    𝘴
    1.17
    უ
    1.16
    POSITIVE LOGITS
     Hamlet
    1.07
     দখলে
    0.98
    ться
    0.95
     odb
    0.92
    意志
    0.92
     lontano
    0.92
    OM
    0.92
    であることを
    0.91
    aec
    0.90
     vra
    0.90
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.