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

    Neuronpedia

    INDEX
    Explanations

    makes you believe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.43
     metallic
    0.42
     brawl
    0.41
     jumped
    0.41
     mashed
    0.41
     whiff
    0.41
     bogged
    0.40
     winter
    0.40
     puncture
    0.40
     leapt
    0.39
    POSITIVE LOGITS
     Mereka
    0.57
     آنها
    0.54
    它们
    0.53
     ඒවා
    0.51
    它們
    0.50
    それが
    0.50
     તેઓ
    0.49
    them
    0.49
     mereka
    0.48
    พวกเขา
    0.48
    Act Density 0.004%

    No Known Activations