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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    principal
    0.64
    begin
    0.64
    Notes
    0.64
    numer
    0.64
    fest
    0.64
    Next
    0.63
    properties
    0.63
    notes
    0.63
    疃
    0.63
    City
    0.62
    POSITIVE LOGITS
     Embora
    0.69
     인도
    0.67
     COMPAR
    0.63
     wú
    0.63
     αὐ
    0.62
     recommending
    0.61
     Marathi
    0.60
     Debido
    0.60
     불구하고
    0.60
    ऽ
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.