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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     городской
    0.53
     Burundi
    0.53
    cadilly
    0.51
     welds
    0.51
     ставак
    0.51
     სახელმწიფ
    0.48
     endeavour
    0.48
     życiu
    0.48
     гульнявыя
    0.48
    คองโก
    0.48
    POSITIVE LOGITS
    0
    0.50
    ẫu
    0.48
    同
    0.46
    رك
    0.45
    setPreferred
    0.43
    1
    0.42
    9
    0.42
    ike
    0.41
    تر
    0.41
    6
    0.41
    Act Density 0.000%

    No Known Activations