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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     twins
    -0.30
     twin
    -0.30
    gaard
    -0.27
    èijĨ
    -0.27
    raid
    -0.26
    ufen
    -0.26
     backs
    -0.26
    anium
    -0.25
     Twins
    -0.25
    ลà¸Ńà¸ĩ
    -0.25
    POSITIVE LOGITS
     vein
    0.27
    ilk
    0.26
    éĶĢ
    0.26
    次ä¼ļè®®
    0.25
    x
    0.24
    isl
    0.24
    plan
    0.24
    hei
    0.23
     London
    0.23
    æĬ½åıĸ
    0.23
    Act Density 2.880%

    No Known Activations

    This feature has no known activations.