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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     също
    0.96
     همچنین
    0.91
     lainnya
    0.89
    elijk
    0.87
     serta
    0.86
    alities
    0.84
    ﺮ
    0.83
     microorganisms
    0.82
    een
    0.79
     nahezu
    0.79
    POSITIVE LOGITS
    ரா
    0.98
    ো
    0.94
     początku
    0.93
    羽
    0.92
    يء
    0.92
    Poppins
    0.91
     mín
    0.86
    oretically
    0.86
    नो
    0.86
    rawdę
    0.86
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.