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

    Neuronpedia

    INDEX
    Explanations

    battery lock

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pork
    0.48
    ற்கு
    0.41
     spaghetti
    0.41
     checkers
    0.41
     computational
    0.40
     enforcing
    0.40
     torre
    0.40
    형
    0.39
     column
    0.39
     monolithic
    0.39
    POSITIVE LOGITS
     Sustainability
    0.46
     अल्
    0.45
    Sustainability
    0.44
     are
    0.43
    Privacy
    0.43
    нский
    0.43
    4
    0.41
     স্ম
    0.41
     bahkan
    0.40
    खरी
    0.40
    Act Density 0.000%

    No Known Activations