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

    Neuronpedia

    INDEX
    Explanations

    "tol" and "tolerance"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unfortunate
    -0.08
     Vive
    -0.08
     vendor
    -0.08
     waving
    -0.08
     hips
    -0.08
     memorial
    -0.07
     racial
    -0.07
     stats
    -0.07
    -0.07
    Jimmy
    -0.07
    POSITIVE LOGITS
     원하는
    0.09
     Desired
    0.09
     seseorang
    0.09
     تحقق
    0.08
    达到
    0.08
     수준
    0.08
     민
    0.08
     누
    0.08
     자신
    0.08
     داشتن
    0.08
    Act Density 0.006%
    No Known Activations