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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    кою
    0.99
    féle
    0.97
     puta
    0.95
    &=\
    0.93
    をした
    0.93
    べき
    0.90
    ী
    0.89
    нибудь
    0.88
    ンの
    0.88
     لازم
    0.88
    POSITIVE LOGITS
    ס
    1.07
    PR
    0.94
     Bereits
    0.90
     After
    0.89
    CA
    0.88
    transition
    0.88
     Additionally
    0.88
     Delivering
    0.88
     Lockdown
    0.86
    HA
    0.85
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.