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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     quickly
    0.99
    Bash
    0.94
     به‌
    0.93
    On
    0.93
     Bash
    0.92
     On
    0.91
    ه‌
    0.90
     on
    0.89
     Method
    0.88
     Mode
    0.87
    POSITIVE LOGITS
    di
    0.84
    dri
    0.82
     सीई
    0.77
     AVE
    0.74
    rivation
    0.74
    頨
    0.74
     PTE
    0.73
    dech
    0.73
    serr
    0.72
     PLHIV
    0.71
    Act Density 0.000%

    No Known Activations