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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     mimetype
    0.71
    িবদ্ধ
    0.70
     dosage
    0.68
     طويل
    0.64
    页面存档备份
    0.63
     uitvoering
    0.63
     wrongdoing
    0.63
     noemen
    0.62
    ള്
    0.61
     board
    0.61
    POSITIVE LOGITS
    𝒓
    0.86
    𝘱
    0.85
     ชุด
    0.81
    𝑟
    0.80
    pairs
    0.80
    𝘺
    0.79
    𝙩
    0.79
    tuples
    0.78
    álaga
    0.75
    टावा
    0.75
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.