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

    Neuronpedia

    INDEX
    Explanations

    pay

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ﰒ
    -0.08
    unicode
    -0.07
    <Location
    -0.07
     schle
    -0.07
     metaData
    -0.07
    	context
    -0.07
    LowerCase
    -0.07
     вра
    -0.07
    athi
    -0.07
     вла
    -0.07
    POSITIVE LOGITS
    心仪的
    0.07
    ihat
    0.07
     repar
    0.07
    (()=>{↵
    0.07
    扰
    0.07
    iable
    0.07
    Seeder
    0.07
    Other
    0.07
    這些
    0.07
    izable
    0.07
    Act Density 0.009%

    No Known Activations