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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    r
    1.02
    ’
    0.98
    j
    0.90
    at
    0.81
    ere
    0.81
    iyat
    0.80
     ليس
    0.80
    mn
    0.79
    0
    0.79
    ată
    0.78
    POSITIVE LOGITS
    而在
    0.80
    BlockUsed
    0.79
    埒
    0.75
    CHES
    0.72
    人士
    0.71
     Anschließend
    0.71
     décidé
    0.70
    滸
    0.70
    VING
    0.69
    以便
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.