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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     उपनिवेश
    0.37
    strftime
    0.36
     nisi
    0.36
     Bachelor
    0.35
    াধ্য
    0.34
     conversely
    0.34
     Conversely
    0.34
    SAME
    0.34
    珐
    0.33
    ardan
    0.33
    POSITIVE LOGITS
    bong
    0.55
     bong
    0.50
     bóng
    0.49
    蒿
    0.47
     Bong
    0.45
     Joon
    0.41
    cloud
    0.41
    Bounds
    0.40
     météor
    0.39
     Bóng
    0.39
    Act Density 0.000%

    No Known Activations