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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     trellis
    0.83
     choir
    0.80
     dictionary
    0.79
    ীন্দ্র
    0.78
     utilises
    0.77
     method
    0.77
     uczni
    0.77
     dictatorship
    0.77
     ought
    0.75
     supposition
    0.75
    POSITIVE LOGITS
    속
    0.73
     лиц
    0.72
    math
    0.71
    вання
    0.71
     прош
    0.70
    상
    0.70
    cas
    0.69
    OF
    0.68
    cer
    0.68
    ง
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.