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

    Neuronpedia

    INDEX
    Explanations

    job titles and professional roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hedra
    0.85
     tyranny
    0.77
     politicians
    0.77
     absurdity
    0.73
    forbidden
    0.72
    Introduceti
    0.72
     macroscopic
    0.71
    uigen
    0.70
    တော်
    0.70
    Keg
    0.68
    POSITIVE LOGITS
     Specialist
    1.56
     specialist
    1.50
     Analyst
    1.44
    助理
    1.38
     specialising
    1.38
     Skills
    1.37
     specializing
    1.37
     Roles
    1.37
     متخصص
    1.37
     freelance
    1.36
    Act Density 0.270%

    No Known Activations