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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     delivers
    0.51
     walks
    0.50
     \\
    0.47
     Donor
    0.46
     Vel
    0.46
     Walks
    0.45
     Performs
    0.45
     -
    0.45
     walked
    0.44
     Schild
    0.44
    POSITIVE LOGITS
     سوی
    0.48
    thm
    0.47
     raro
    0.46
    となり
    0.46
     tampilan
    0.46
    Louisiana
    0.45
    aside
    0.45
    स्वर
    0.44
     contas
    0.43
    Blooming
    0.43
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.