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

    Neuronpedia

    INDEX
    Explanations

    matrix transposition and algebra

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Turtle
    -0.08
    -yourself
    -0.07
     pro
    -0.07
     hjäl
    -0.07
     brush
    -0.07
     Seigneur
    -0.07
    ankar
    -0.07
     ruling
    -0.07
     conveyed
    -0.07
     decoration
    -0.07
    POSITIVE LOGITS
    Transpose
    0.11
    transpose
    0.10
     transpose
    0.10
    (face
    0.09
     võ
    0.08
     wissenschaft
    0.08
    Bom
    0.07
     rosto
    0.07
    undo
    0.07
     ATL
    0.07
    Act Density 0.003%

    No Known Activations