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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    n
    0.98
    ק
    0.95
    ਾਰ
    0.91
     jardim
    0.91
    j
    0.90
    彡
    0.87
    手机
    0.87
     biasa
    0.85
     joten
    0.85
     stato
    0.84
    POSITIVE LOGITS
    due
    0.66
    挽
    0.64
    ⤦
    0.61
     tenders
    0.60
     Obwohl
    0.59
     baš
    0.59
     اثر
    0.58
     altercation
    0.58
     exaggerate
    0.58
    详情
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.