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

    Neuronpedia

    INDEX
    Explanations

    Underground utilities/construction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     #
    -0.06
     trousers
    -0.06
    ブ
    -0.06
    -0.06
     give
    -0.06
     gives
    -0.06
     Barnes
    -0.06
     conservatism
    -0.06
     Turn
    -0.06
     Paul
    -0.06
    POSITIVE LOGITS
    ασία
    0.07
     QAction
    0.06
     comrades
    0.06
     InternalEnumerator
    0.06
    فات
    0.06
    เสน
    0.06
     libc
    0.06
     obsessed
    0.06
     {|
    0.06
     ncols
    0.06
    Act Density 0.079%

    No Known Activations