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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ا
    0.93
    ر
    0.91
    л
    0.85
     پیسو
    0.82
    𝓲
    0.81
    الح
    0.79
     ужа
    0.75
    в
    0.75
    ві
    0.75
    ه
    0.75
    POSITIVE LOGITS
     flanked
    0.79
     female
    0.78
     Provinz
    0.78
     collaboratively
    0.76
     ámbito
    0.74
     shaped
    0.73
     tú
    0.73
     one
    0.72
     detectives
    0.71
     roaming
    0.71
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.