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

    Neuronpedia

    INDEX
    Explanations

    dialogue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )||(
    -0.07
     vin
    -0.07
     productId
    -0.07
    小编
    -0.07
     vending
    -0.07
     IOS
    -0.07
    面包
    -0.06
    '↵
    -0.06
    人员
    -0.06
    .likes
    -0.06
    POSITIVE LOGITS
     haute
    0.08
    uli
    0.07
     pub
    0.07
    aktu
    0.07
    陞
    0.07
    अ
    0.07
     ballo
    0.06
     rebut
    0.06
    מעשה
    0.06
     Dav
    0.06
    Act Density 0.135%

    No Known Activations