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

    Neuronpedia

    INDEX
    Explanations

    と

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    455
    -0.07
    кор
    -0.06
     "{}
    -0.06
    =admin
    -0.06
     geniş
    -0.06
    nio
    -0.06
     bree
    -0.06
     deniz
    -0.06
     　　　　　　　　　　
    -0.06
    erro
    -0.06
    POSITIVE LOGITS
    plat
    0.07
     Fuse
    0.07
    と
    0.07
    Matches
    0.06
    tenant
    0.06
    укт
    0.06
     وضع
    0.06
    at
    0.06
    ิต
    0.06
    không
    0.06
    Act Density 0.005%

    No Known Activations