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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    응
    1.03
    वादी
    1.01
    িয়ান
    1.01
    воз
    1.00
    ید
    0.99
    Hey
    0.96
    ج
    0.95
     Soak
    0.95
     angegeben
    0.93
    ൃ
    0.93
    POSITIVE LOGITS
    有利于
    1.31
     дорогие
    1.26
    estima
    1.24
     composition
    1.23
     distinguishing
    1.22
    ্জন
    1.17
    esley
    1.16
    kład
    1.14
    𝘺
    1.13
     nineties
    1.12
    Act Density 0.000%

    No Known Activations