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

    Neuronpedia

    INDEX
    Explanations

    Lemon Herb, poetic verse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    会儿
    0.39
    Transient
    0.38
     ketemu
    0.38
    прочем
    0.37
    Forward
    0.37
     આવ્યો
    0.36
     MOBILE
    0.36
    Meet
    0.36
    ันท
    0.36
     Guerr
    0.35
    POSITIVE LOGITS
    ডেট
    0.45
    menuStrip
    0.41
     購入
    0.41
     viewed
    0.41
    ayah
    0.40
    າຍ
    0.39
     unsupervised
    0.39
     supervis
    0.39
    irtual
    0.38
     فر
    0.38
    Act Density 0.005%

    No Known Activations