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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ненави
    0.45
    ТЕ
    0.44
    Ⴀ
    0.43
    უცი
    0.42
    引领
    0.41
    тья
    0.40
     DETER
    0.40
     کرد
    0.40
    слен
    0.39
    ㄆ
    0.39
    POSITIVE LOGITS
     চেয়ারম্যান
    0.39
     esimerkiksi
    0.38
    cien
    0.37
    adena
    0.37
     smashing
    0.37
     Tier
    0.36
     Tim
    0.36
    ગવાન
    0.36
     hardworking
    0.36
     nada
    0.35
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.