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

    Neuronpedia

    INDEX
    Explanations

    job roles and opportunities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     uniformly
    0.79
     occupations
    0.75
     लेसन
    0.72
     humiliating
    0.66
     bosses
    0.66
     stubbornly
    0.65
     humiliation
    0.64
     incomes
    0.63
    ออกจาก
    0.63
     pessimism
    0.63
    POSITIVE LOGITS
     oportunidade
    1.34
     exciting
    1.34
    Join
    1.33
     join
    1.30
     Join
    1.22
     opportunity
    1.18
     joining
    1.16
    opportunity
    1.15
    Opportunity
    1.14
    Joining
    1.14
    Act Density 0.296%

    No Known Activations