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

    Neuronpedia

    INDEX
    Explanations

    AI-trying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     :
    0.49
    是我们
    0.39
     /*
    0.38
     signOut
    0.38
     mengg
    0.38
    歆
    0.37
    Ek
    0.36
     bounding
    0.36
     soin
    0.36
     enunci
    0.35
    POSITIVE LOGITS
    random
    0.41
    εύ
    0.41
    竪
    0.40
    experimental
    0.40
    팝
    0.37
    gateway
    0.37
    IDA
    0.36
    ቫ
    0.36
     पश्च
    0.36
     пути
    0.36
    Act Density 0.000%

    No Known Activations