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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    НА
    1.00
     WAST
    0.98
    SizeMode
    0.96
    ură
    0.91
    かける
    0.90
    𝑺
    0.90
     AG
    0.89
     hangat
    0.89
     मिला
    0.89
    かけた
    0.88
    POSITIVE LOGITS
    cx
    1.10
    计划
    1.02
    missive
    0.94
    know
    0.94
    e
    0.93
    cause
    0.91
    gathering
    0.89
    prone
    0.89
    commission
    0.89
    crt
    0.89
    Act Density 0.000%

    No Known Activations