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

    Neuronpedia

    INDEX
    Explanations

    legal and financial terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Totals
    1.06
    ?!?
    1.01
     Kaliforn
    0.97
     Zelda
    0.96
    actic
    0.95
     undead
    0.95
     behaviors
    0.95
    自分の
    0.92
     neurologic
    0.92
     nighttime
    0.91
    POSITIVE LOGITS
     upto
    2.05
     till
    1.90
     lakh
    1.89
     saree
    1.87
     Gandhiji
    1.85
     Maharashtra
    1.85
     Andhra
    1.82
     Odisha
    1.82
     sarees
    1.80
     Gujarat
    1.80
    Act Density 0.139%

    No Known Activations