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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     wher
    0.51
     extravagant
    0.48
     kdo
    0.48
    𝙥
    0.46
    Ꮯ
    0.46
    𝕌
    0.46
    𝑔
    0.46
     lemon
    0.45
    0.45
    𝒑
    0.45
    POSITIVE LOGITS
     അരി
    0.47
    uš
    0.46
    ö
    0.46
    ürz
    0.45
     unserer
    0.44
     unserem
    0.43
     ihrer
    0.43
    ü
    0.43
    Basis
    0.43
     früheren
    0.43
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.