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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    liferation
    0.36
    当選
    0.36
     Weed
    0.35
    вості
    0.34
     ಆಗ
    0.34
     계
    0.33
     כמה
    0.33
     સો
    0.32
    擋
    0.32
     olsa
    0.32
    POSITIVE LOGITS
    aren
    0.48
    Ez
    0.47
    iei
    0.43
    ez
    0.42
     bere
    0.41
    itzen
    0.41
    ekin
    0.41
    rean
    0.41
     zer
    0.40
     eta
    0.40
    Act Density 0.000%

    No Known Activations