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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    c
    0.65
    la
    0.64
    iy
    0.57
    ky
    0.55
    ks
    0.52
    cy
    0.52
    er
    0.52
    ash
    0.52
    nj
    0.51
    ling
    0.51
    POSITIVE LOGITS
    나
    0.61
    하도록
    0.54
     ಸಾಧ್ಯ
    0.49
    ALE
    0.48
     változat
    0.47
    𝘼
    0.46
     sixty
    0.46
    어나
    0.46
     اندازه
    0.45
    나가
    0.45
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.