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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ע
    0.51
    اج
    0.47
     faaliyet
    0.47
     theorem
    0.46
     uttered
    0.45
     piano
    0.44
     penthouse
    0.44
    原子炉
    0.44
     heightened
    0.44
     داستان
    0.44
    POSITIVE LOGITS
     부분
    0.58
     أصبح
    0.48
     allé
    0.48
     Allow
    0.45
    俻
    0.45
    ROWS
    0.45
     Hath
    0.44
    之后的
    0.44
     incor
    0.43
     Vire
    0.43
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.