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

    Neuronpedia

    INDEX
    Explanations

    spatial orientation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Official
    -0.09
     Naked
    -0.08
     Innoc
    -0.08
    Official
    -0.08
     Button
    -0.07
     Lazar
    -0.07
     honorable
    -0.07
     nicer
    -0.07
     EIF
    -0.07
     official
    -0.07
    POSITIVE LOGITS
    纵
    0.13
     spatial
    0.13
     horizontally
    0.12
     vertical
    0.11
    vertical
    0.11
     sideways
    0.11
     temporal
    0.11
    horizontal
    0.11
     verticale
    0.11
    .horizontal
    0.11
    Act Density 0.066%

    No Known Activations