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

    Neuronpedia

    INDEX
    Explanations

    Chemical reactions/patents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    都不会
    -0.07
    深受
    -0.07
     evacuate
    -0.07
    URATION
    -0.06
    REF
    -0.06
     Omaha
    -0.06
     khấu
    -0.06
     Inspiration
    -0.06
    .From
    -0.06
    SPORT
    -0.06
    POSITIVE LOGITS
     bad
    0.08
     Au
    0.07
     lead
    0.07
     cl
    0.07
     carrot
    0.07
    .mj
    0.07
    	b
    0.07
    kb
    0.07
     leads
    0.07
    jących
    0.07
    Act Density 0.120%

    No Known Activations