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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    at
    1.30
    re
    1.19
    est
    1.19
    du
    1.12
      
    1.12
    l
    1.06
    la
    0.99
    ten
    0.96
    लोग
    0.96
    ell
    0.94
    POSITIVE LOGITS
    璺
    1.35
     situaciones
    1.29
    彠
    1.28
     avaliar
    1.25
     पिछले
    1.23
     平成
    1.23
    随后
    1.22
    ὡ
    1.21
     Decide
    1.20
    subdir
    1.20
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.