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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     countrymen
    0.47
     Present
    0.46
    u
    0.45
     RSVP
    0.44
    vegan
    0.42
     marina
    0.42
     vegan
    0.41
    </li>
    0.41
    ர்ப்ப
    0.41
     Probate
    0.41
    POSITIVE LOGITS
    ᔪ
    0.51
    }$-(
    0.50
    молча
    0.49
    𝔱
    0.49
    आइ
    0.48
    𝔞
    0.48
    دید
    0.47
    ：（
    0.46
    ণির
    0.46
    ק
    0.45
    Act Density 0.001%

    No Known Activations