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

    Neuronpedia

    INDEX
    Explanations

    equity, equality, and inclusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ជាប់
    0.45
     अनुर
    0.40
     virgin
    0.40
     temptation
    0.38
     immature
    0.37
     indirectly
    0.37
     debugging
    0.37
     fascin
    0.36
     unripe
    0.36
    薀
    0.36
    POSITIVE LOGITS
     equitable
    2.02
     equality
    2.00
     equity
    1.91
     Equality
    1.73
    Equality
    1.73
     inclusivity
    1.73
    equality
    1.70
     igualdad
    1.70
    equity
    1.67
     Equity
    1.66
    Act Density 0.082%

    No Known Activations