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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Những
    1.49
     sanitaire
    1.38
    <unused2041>
    1.30
    嚓
    1.28
    下图
    1.28
    诸多
    1.27
    هار
    1.27
    kinase
    1.26
     이런
    1.26
    如图
    1.25
    POSITIVE LOGITS
    la
    1.05
    }$
    1.04
     dece
    1.00
    ia
    1.00
    omb
    0.99
    iają
    0.99
    ab
    0.97
    ittel
    0.96
    ine
    0.91
    omas
    0.90
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.