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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    edList
    -0.26
    [result
    -0.25
    âĢ¦↵↵↵↵
    -0.24
    tá
    -0.24
     unab
    -0.24
    continent
    -0.24
    ...↵↵↵↵
    -0.23
    è¿Ľåĩº
    -0.23
     оÑĩеÑĢедÑĮ
    -0.23
     misd
    -0.23
    POSITIVE LOGITS
    ptic
    0.29
    =".
    0.26
    家å±ħ
    0.25
    ä¸IJ
    0.25
    æĸ
    0.24
    opol
    0.24
    çĶŁ
    0.24
    straints
    0.24
    sin
    0.24
    平淡
    0.24
    Act Density 0.010%

    No Known Activations

    This feature has no known activations.