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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    PL
    0.45
     LIABILITY
    0.43
    ரிக்க
    0.43
     discontinuity
    0.42
    ToRemove
    0.41
     secundarios
    0.40
    ቁ
    0.40
    ENO
    0.39
     deficit
    0.39
     चाचा
    0.39
    POSITIVE LOGITS
    ကြည်
    0.47
     புரிய
    0.46
    ırken
    0.45
    时间内
    0.44
     optimizing
    0.43
     hemispheres
    0.42
     અનુભ
    0.42
    \|^
    0.42
     实现
    0.41
    威
    0.41
    Act Density 0.001%

    No Known Activations