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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     on
    1.29
    х
    1.05
    та
    1.01
    то
    0.99
    اك
    0.99
    ان
    0.98
    스
    0.97
    ак
    0.96
    д
    0.95
    دين
    0.92
    POSITIVE LOGITS
    1
    1.09
    2
    0.98
    EN
    0.93
    I
    0.84
    US
    0.82
    ES
    0.80
    reg
    0.80
    O
    0.79
    IP
    0.79
     I
    0.77
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.