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

    Neuronpedia

    INDEX
    Explanations

    /Getty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Раз
    -0.07
     carbon
    -0.07
    окрем
    -0.07
    Carbon
    -0.07
     bậc
    -0.07
     cortisol
    -0.07
    Cls
    -0.06
    .radians
    -0.06
    _acc
    -0.06
    声
    -0.06
    POSITIVE LOGITS
    Segment
    0.07
     <*
    0.06
     seize
    0.06
    _New
    0.06
     Wealth
    0.06
    єн
    0.06
     Magick
    0.06
     Hey
    0.06
     Fraction
    0.06
     Buckingham
    0.06
    Act Density 0.001%

    No Known Activations