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

    Neuronpedia

    INDEX
    Explanations

    diversity and inclusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dandruff
    0.44
     molecule
    0.43
     rubble
    0.41
     atom
    0.41
     ether
    0.40
     cellulose
    0.40
     trousers
    0.40
     scathing
    0.40
     ventric
    0.40
     cravings
    0.40
    POSITIVE LOGITS
    Diversity
    0.65
     Diversity
    0.60
    diversity
    0.57
     diversity
    0.54
    candidate
    0.53
    Employee
    0.53
    Equal
    0.52
    Employees
    0.51
     Employees
    0.50
    Applicant
    0.50
    Act Density 0.016%

    No Known Activations