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

    Neuronpedia

    INDEX
    Explanations

    luring, lulled, lingo, lacks, liveness, lurches

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     L
    0.55
     LI
    0.54
    Л
    0.54
     الل
    0.50
    𝗟
    0.49
     LR
    0.48
     LM
    0.48
     LA
    0.47
     Lu
    0.47
     LT
    0.47
    POSITIVE LOGITS
    গে
    0.53
    ighter
    0.50
    ifestyles
    0.49
    ighters
    0.48
    Og
    0.44
    िरिक्स
    0.44
    irge
    0.44
    leading
    0.43
     arginine
    0.43
    IEEE
    0.43
    Act Density 0.008%

    No Known Activations