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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     lures
    0.57
    '
    0.55
    ni
    0.52
    th
    0.50
    primary
    0.49
    la
    0.47
     gloss
    0.46
    ien
    0.46
    ectin
    0.46
    toi
    0.46
    POSITIVE LOGITS
    нным
    0.51
    ويلة
    0.49
    ス
    0.46
    uestas
    0.44
    льним
    0.44
    تے
    0.43
    출
    0.43
    ونو
    0.42
    会い
    0.42
    રાજ
    0.42
    Act Density 0.000%

    No Known Activations