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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    𝐀
    1.45
    𝗜
    1.31
    𝐑
    1.22
    𝐄
    1.20
    𝓌
    1.19
    И
    1.19
    𝙄
    1.18
    𝚃
    1.17
    েন্দ্রনাথ
    1.17
    quantile
    1.17
    POSITIVE LOGITS
    م
    1.06
    odigd
    1.04
    kiego
    0.98
    man
    0.96
     adhered
    0.93
    이니
    0.92
    い
    0.92
     nibb
    0.91
    को
    0.91
     inactivated
    0.89
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.