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

    Neuronpedia

    INDEX
    Explanations

    .com

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    沃尔
    -0.07
    天国
    -0.07
    alink
    -0.07
    不舍
    -0.06
    �
    -0.06
     lạc
    -0.06
    .tolist
    -0.06
     MATCH
    -0.06
    [r
    -0.06
    穿梭
    -0.06
    POSITIVE LOGITS
     rhe
    0.06
    }`
    0.06
     CP
    0.06
    кая
    0.06
     dieta
    0.06
     bug
    0.06
    forme
    0.06
     Diamonds
    0.06
    ernals
    0.06
    建立健全
    0.06
    Act Density 0.001%

    No Known Activations