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

    Neuronpedia

    INDEX
    Explanations

    environment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Transpose
    -0.09
    transpose
    -0.08
     épr
    -0.08
     Uphol
    -0.08
     talleres
    -0.08
     redistribute
    -0.07
     Established
    -0.07
     bidi
    -0.07
    Employ
    -0.07
     wills
    -0.07
    POSITIVE LOGITS
     ഭൂ
    0.09
     Earth
    0.08
     അട
    0.08
    ക്കാര
    0.08
     sweeter
    0.08
    .constants
    0.08
     masked
    0.08
    .Constants
    0.08
     പങ്ക
    0.08
    earth
    0.08
    Act Density 0.005%

    No Known Activations