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

    Neuronpedia

    INDEX
    Explanations

    site-packages and calculating years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    خر
    0.39
     Bones
    0.39
     KA
    0.38
     Egg
    0.36
     Kong
    0.36
     Literally
    0.36
     Maybe
    0.35
     учё
    0.35
    杆
    0.35
     Tum
    0.35
    POSITIVE LOGITS
     afraid
    0.38
     ক্রিকেট
    0.38
     barat
    0.38
    oclip
    0.38
     calci
    0.38
    ினி
    0.37
    ਡੀ
    0.37
     personalise
    0.37
     hairstyles
    0.37
     imageName
    0.37
    Act Density 0.000%

    No Known Activations