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

    Neuronpedia

    INDEX
    Explanations

    employ

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tracing
    -0.08
     creates
    -0.07
     determines
    -0.07
     traced
    -0.07
     variance
    -0.07
     Curtis
    -0.07
     creating
    -0.07
    “At
    -0.07
     Rita
    -0.07
     Truth
    -0.07
    POSITIVE LOGITS
     employed
    0.13
     employ
    0.09
     employing
    0.08
     employs
    0.08
     adopted
    0.08
    osp
    0.07
     appointed
    0.07
     Spy
    0.07
     mediante
    0.07
     Employ
    0.07
    Act Density 0.006%

    No Known Activations