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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     vielfält
    0.88
     anticancer
    0.81
     câncer
    0.77
     Stateless
    0.76
     Elektrokh
    0.76
     canciones
    0.75
     activités
    0.75
     ovipares
    0.73
     comedians
    0.72
     musicals
    0.71
    POSITIVE LOGITS
    （
    0.72
     (
    0.69
    on
    0.64
    ت
    0.60
    ופן
    0.59
     reserve
    0.58
     сво
    0.57
    ซึ่ง
    0.57
     новом
    0.57
     পশ্চিম
    0.56
    Act Density 0.000%

    No Known Activations