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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     montana
    1.16
     somehow
    1.07
    glied
    1.01
     Ders
    0.97
     pierre
    0.97
     translateY
    0.96
     ongel
    0.95
    gium
    0.94
    dden
    0.94
    ti
    0.94
    POSITIVE LOGITS
    郸
    1.31
    cough
    1.29
     वर्णित
    1.27
    attached
    1.27
    started
    1.24
    served
    1.24
    careers
    1.23
    reduced
    1.22
     बकाया
    1.21
    ر
    1.20
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.