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

    Neuronpedia

    INDEX
    Explanations

    piecewise functions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     anges
    -0.08
     Gly
    -0.08
     genetics
    -0.08
     overcoming
    -0.07
     Fortsch
    -0.07
     Sess
    -0.07
     elimination
    -0.07
     inoc
    -0.07
    قدم
    -0.07
     niv
    -0.07
    POSITIVE LOGITS
     stitched
    0.09
     стих
    0.09
    Undefined
    0.08
     Undefined
    0.08
    Piece
    0.08
    域
    0.08
    、中
    0.08
     undefined
    0.08
    條
    0.08
     dehors
    0.08
    Act Density 0.059%

    No Known Activations