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

    Neuronpedia

    INDEX
    Explanations

    employment law

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     organizations
    -0.07
     insulation
    -0.07
     قدرت
    -0.07
     consumo
    -0.07
     має
    -0.07
    -authored
    -0.06
     اصفه
    -0.06
     compute
    -0.06
     公司
    -0.06
    โค
    -0.06
    POSITIVE LOGITS
    Southern
    0.07
    method
    0.07
    ?'
    0.06
    .destroy
    0.06
    	assertThat
    0.06
    ?’
    0.06
    lever
    0.06
    ään
    0.06
    लत
    0.06
     Chevron
    0.06
    Act Density 0.019%

    No Known Activations