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

    Neuronpedia

    INDEX
    Explanations

    What is their

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bacilli
    0.42
     endet
    0.40
     emotional
    0.39
     grat
    0.39
    }|^
    0.39
     അവസ്ഥ
    0.38
     toxin
    0.38
     :'
    0.38
     errore
    0.38
     ingot
    0.38
    POSITIVE LOGITS
     Satellite
    0.45
    Satellite
    0.41
    Tasks
    0.40
     Directions
    0.38
    Country
    0.38
     тыся
    0.38
     Zoning
    0.38
    Saturday
    0.37
     सिराज
    0.37
     Regularly
    0.37
    Act Density 0.000%

    No Known Activations