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

    Neuronpedia

    INDEX
    Explanations

    range

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    OUNTRY
    -0.07
     브
    -0.07
     Extraction
    -0.07
    -find
    -0.07
     لت
    -0.06
     депут
    -0.06
     buffer
    -0.06
    SEO
    -0.06
    orientation
    -0.06
    进行
    -0.06
    POSITIVE LOGITS
    کیل
    0.06
     til
    0.06
    ุ์
    0.06
     exemptions
    0.06
     apologized
    0.06
    Vis
    0.06
    .central
    0.06
    Rus
    0.06
    +s
    0.06
     mange
    0.06
    Act Density 0.007%

    No Known Activations