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

    Neuronpedia

    INDEX
    Explanations

    custom image to use

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     largely
    0.38
     республики
    0.37
     exportation
    0.36
    ))}
    0.36
     quedaría
    0.36
     रखे
    0.35
     mensual
    0.35
     encompassed
    0.35
     analyses
    0.34
     техни
    0.34
    POSITIVE LOGITS
    ত্যার
    0.46
     ለማ
    0.41
     XNUMX
    0.41
     ​​​​
    0.40
     Incidentally
    0.39
    bellion
    0.38
     Lyon
    0.38
     بيه
    0.38
    檚
    0.38
     WIB
    0.37
    Act Density 0.002%

    No Known Activations