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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    П
    2.11
    ب
    2.03
    स
    1.87
    ного
    1.87
    ление
    1.71
    う
    1.62
     verdade
    1.61
    ных
    1.60
    ी
    1.59
    на
    1.57
    POSITIVE LOGITS
    ल्पनिक
    1.87
     treacher
    1.72
     والم
    1.70
     punishing
    1.70
    managedbuild
    1.68
    পূর্ব
    1.65
     ludicrous
    1.64
     slush
    1.64
    ){\
    1.63
    uiDesigner
    1.63
    Act Density 0.001%

    No Known Activations