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

    Neuronpedia

    INDEX
    Explanations

    population percentages and groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pensions
    0.92
     activist
    0.89
     aspirant
    0.88
     voice
    0.85
     ennemis
    0.84
     ambition
    0.83
     graduation
    0.83
     inclusivity
    0.83
     mindset
    0.82
     winnings
    0.81
    POSITIVE LOGITS
     humans
    0.90
     Arabidopsis
    0.90
    وسک
    0.90
    icklabels
    0.82
     людини
    0.81
     thaliana
    0.80
     autopsy
    0.80
    ntgen
    0.79
     ವ್ಯ
    0.79
     rodents
    0.78
    Act Density 0.316%

    No Known Activations