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

    Neuronpedia

    INDEX
    Explanations

    greens, beige, feed, specific feature

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     गोइंग
    0.43
    ینگ
    0.41
    це
    0.40
     سبسڈی
    0.40
     phosphorylated
    0.39
     pounds
    0.39
     zorg
    0.38
     মর্টার
    0.38
     tani
    0.38
     lyd
    0.38
    POSITIVE LOGITS
    RunWith
    0.39
     एप्ली
    0.37
    申
    0.37
    aiman
    0.36
    te
    0.36
    mm
    0.35
     בא
    0.35
     ثبت
    0.35
     tweepy
    0.35
     “
    0.34
    Act Density 0.000%

    No Known Activations