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

    Neuronpedia

    INDEX
    Explanations

    secure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dsp
    -0.07
    ToEnd
    -0.07
    	size
    -0.07
     flew
    -0.06
    努力
    -0.06
    而
    -0.06
     розвитку
    -0.06
    working
    -0.06
    кадем
    -0.06
    istributor
    -0.06
    POSITIVE LOGITS
     overhead
    0.07
     typu
    0.06
     JADX
    0.06
     Fleming
    0.06
     diplom
    0.06
     heavenly
    0.06
     Dictionary
    0.06
    ismatch
    0.06
     dispose
    0.06
     Toshiba
    0.06
    Act Density 0.021%

    No Known Activations