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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ﻱ
    0.39
    ﺽ
    0.36
     Notation
    0.34
     Concerning
    0.34
    ounced
    0.34
     (%)
    0.34
    မဟုတ်
    0.34
    ﺡ
    0.34
     Limitations
    0.33
    ﺝ
    0.33
    POSITIVE LOGITS
    drug
    0.38
    data
    0.37
    es
    0.37
     our
    0.35
    ijn
    0.35
    validate
    0.35
    we
    0.35
    RO
    0.34
    buf
    0.34
     nuestras
    0.34
    Act Density 0.007%

    No Known Activations