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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Cinema
    -0.08
    ến
    -0.07
    .HorizontalAlignment
    -0.07
    뤠
    -0.07
     Serena
    -0.07
    [B
    -0.06
    nette
    -0.06
    pływ
    -0.06
    .AddParameter
    -0.06
    𬸣
    -0.06
    POSITIVE LOGITS
     splits
    0.07
    back
    0.07
     shocked
    0.07
    Bomb
    0.07
     threads
    0.06
    InstanceId
    0.06
     deflect
    0.06
     eight
    0.06
    Boundary
    0.06
    其中一个
    0.06
    Act Density 0.038%

    No Known Activations