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

    Neuronpedia

    INDEX
    Explanations

    groups of people, statistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    10
    -0.08
    -man
    -0.07
    results
    -0.06
    tabs
    -0.06
    	done
    -0.06
    3
    -0.06
     projects
    -0.06
     nested
    -0.06
    Places
    -0.06
    <i
    -0.06
    POSITIVE LOGITS
     Trotsky
    0.07
    нять
    0.07
    .SpringBootApplication
    0.07
    ráž
    0.07
    emme
    0.07
     UClass
    0.06
    <Response
    0.06
     diferente
    0.06
    >tagger
    0.06
    SESSION
    0.06
    Act Density 0.111%

    No Known Activations