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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    र
    1.07
    ﻪ
    0.99
    ੰ
    0.98
     informé
    0.97
     RET
    0.94
     towarz
    0.92
     ৪৫
    0.91
     saad
    0.90
    
    0.90
     pohod
    0.89
    POSITIVE LOGITS
    en
    1.20
    schutz
    1.19
    ည်း
    1.19
     Luật
    1.18
    <unused979>
    1.17
    不然
    1.17
    killers
    1.15
    प्ताहिक
    1.14
    erus
    1.14
    rägen
    1.14
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.