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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     determinant
    0.97
    lombok
    0.96
    نن
    0.90
     率
    0.90
     OnTrigger
    0.90
    Doom
    0.89
     redistributed
    0.88
     misa
    0.88
    слава
    0.86
     Painted
    0.86
    POSITIVE LOGITS
    us
    1.13
    of
    1.07
    oh
    0.98
    า
    0.97
    হ
    0.93
    ed
    0.86
    an
    0.86
    ว
    0.83
    arg
    0.82
    ادة
    0.79
    Act Density 0.000%

    No Known Activations