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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .Combine
    -0.08
     divergence
    -0.08
     redhead
    -0.07
     coinc
    -0.07
     mưa
    -0.07
     domina
    -0.07
     ‎
    -0.07
     formul
    -0.07
    Nonnull
    -0.07
     nausea
    -0.07
    POSITIVE LOGITS
    -aff
    0.07
    왠
    0.07
    特色社会
    0.07
    -expanded
    0.07
     inconvenient
    0.07
    들과
    0.07
    렌
    0.07
    .effects
    0.06
    -platform
    0.06
    ẅ
    0.06
    Act Density 0.001%

    No Known Activations