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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Alhaji
    0.49
     hydrolysis
    0.46
     наук
    0.44
    中
    0.44
     allegiance
    0.44
    bower
    0.43
     угла
    0.42
    ில்
    0.42
     DOF
    0.41
    atangan
    0.41
    POSITIVE LOGITS
    or
    0.45
    ье
    0.39
    িকভাবে
    0.38
    ాగ
    0.37
    ieurs
    0.37
    től
    0.37
    )$\
    0.37
     pozwoli
    0.37
    er
    0.36
    ဦ
    0.36
    Act Density 0.583%

    No Known Activations