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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    你有
    0.40
    有名
    0.39
    不能
    0.38
    з
    0.37
    你
    0.36
    全部
    0.36
    便宜
    0.36
    은
    0.36
    っ
    0.34
    你是
    0.34
    POSITIVE LOGITS
    ҳои
    0.48
     rehearsal
    0.46
     collaborating
    0.43
    apeutics
    0.42
     Ağustos
    0.42
     τῶν
    0.42
    inspired
    0.41
     affiliated
    0.41
     Már
    0.41
     Christoph
    0.40
    Act Density 0.004%

    No Known Activations