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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     dominions
    0.86
    ochrome
    0.85
     spectra
    0.84
    ものを
    0.81
     repulsion
    0.81
     fortal
    0.80
     ciek
    0.80
     elaborado
    0.80
     gedacht
    0.79
    मीत
    0.79
    POSITIVE LOGITS
    С
    0.78
    リ
    0.78
    Т
    0.75
    д
    0.75
    س
    0.74
    кси
    0.73
    Ро
    0.73
    у
    0.73
    о
    0.73
    dar
    0.72
    Act Density 0.000%

    No Known Activations