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

    Neuronpedia

    INDEX
    Explanations

    workplace issues, culture, retention, wellbeing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    1.12
     as
    1.01
    data
    0.91
    tól
    0.91
    m
    0.91
    ﻭ
    0.89
    ্রম
    0.88
    as
    0.82
    g
    0.82
    se
    0.81
    POSITIVE LOGITS
    )
    1.49
    '
    1.21
    >
    1.13
     workplace
    1.10
     workplaces
    1.03
    ]
    0.97
     Workplace
    0.96
    ).
    0.91
    ust
    0.91
    )،
    0.91
    Act Density 0.005%

    No Known Activations