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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Василь
    0.51
     Sunil
    0.48
    azim
    0.47
    ગાહી
    0.46
     They
    0.46
    ATIONS
    0.45
    abha
    0.45
     Duncan
    0.45
    尉
    0.44
     It
    0.44
    POSITIVE LOGITS
    iske
    0.51
    ռ
    0.49
    iskt
    0.48
    مت
    0.47
    물이
    0.47
    irah
    0.46
    text
    0.46
     font
    0.46
    λ
    0.45
    ନ
    0.45
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.