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

    Neuronpedia

    INDEX
    Explanations

    Quotes/colons

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    陆续
    -0.08
     operators
    -0.08
     abundant
    -0.07
    里
    -0.07
     September
    -0.07
    =url
    -0.07
    开启
    -0.07
    鄜
    -0.07
    四个
    -0.06
     tease
    -0.06
    POSITIVE LOGITS
     טיול
    0.07
     SimpleName
    0.07
    רגיש
    0.06
    (inst
    0.06
    DCALL
    0.06
    ekte
    0.06
    ServiceProvider
    0.06
     שנים
    0.06
    rolling
    0.06
     GI
    0.06
    Act Density 0.052%

    No Known Activations