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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    انه
    1.09
    φή
    1.00
     cùng
    0.99
    ka
    0.96
    ited
    0.93
    ić
    0.93
     взгляд
    0.92
     वो
    0.92
    ૧
    0.91
    ic
    0.91
    POSITIVE LOGITS
    昻
    1.44
     obese
    1.41
     discourse
    1.39
     legible
    1.35
     absorption
    1.35
    师
    1.32
     MongoClient
    1.30
     centerX
    1.29
     discourses
    1.28
     pedal
    1.27
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.