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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    د
    0.49
    Bal
    0.48
    ጐ
    0.47
    Roll
    0.47
    Adv
    0.47
    Wallace
    0.47
    عرض
    0.47
     million
    0.47
    +
    0.47
    ၵ
    0.46
    POSITIVE LOGITS
     રાજ
    0.54
     ahuv
    0.54
     ಯಾರ
    0.52
    letscher
    0.51
    𝓸
    0.51
     思い
    0.50
     ರಾಜ
    0.50
     ಆದ
    0.49
     ಪರ
    0.49
    ぬいぐるみ
    0.48
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.