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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    bies
    1.59
    ៉
    1.34
    ங்கிணை
    1.33
    rotated
    1.30
    linear
    1.27
    ه
    1.21
    bie
    1.19
    linearity
    1.18
    SOL
    1.18
    categorical
    1.17
    POSITIVE LOGITS
    ्यारह
    1.07
    ἱ
    1.07
     senhor
    1.06
    ｙ
    1.05
     aby
    1.04
     trợ
    1.04
    ires
    1.03
     щоб
    1.02
    gridLayout
    1.02
    怀疑
    1.01
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.