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

    Neuronpedia

    INDEX
    Explanations

    space

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ~/.
    -0.08
     fixes
    -0.07
     Reality
    -0.07
     lied
    -0.07
     feas
    -0.07
     badge
    -0.07
     gee
    -0.07
     Realität
    -0.07
    _pb
    -0.07
     Ki
    -0.07
    POSITIVE LOGITS
     foliage
    0.09
    Muh
    0.09
     beautifully
    0.08
     вентиля
    0.08
    unused
    0.08
     unused
    0.08
     thoughtfully
    0.08
     aerodynamic
    0.08
     सुंदर
    0.08
     élégant
    0.08
    Act Density 0.002%

    No Known Activations