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

    Neuronpedia

    INDEX
    Explanations

    bodies of text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    後に
    -0.06
    Level
    -0.06
    ţi
    -0.06
    浅
    -0.06
     bırak
    -0.06
    اویر
    -0.06
     Mor
    -0.06
    üyük
    -0.06
    ↵
↵
↵
    -0.06
    /pop
    -0.06
    POSITIVE LOGITS
    kee
    0.07
     versatile
    0.07
     história
    0.07
     exotic
    0.07
    emplate
    0.06
     wonders
    0.06
     restaurant
    0.06
     زیرا
    0.06
     publishers
    0.06
     sms
    0.06
    Act Density 0.000%

    No Known Activations