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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nhập
    -0.07
    .database
    -0.07
    Sigma
    -0.07
     ]↵
    -0.07
     فهرست
    -0.07
    arp
    -0.06
    Person
    -0.06
    _manual
    -0.06
     Roths
    -0.06
    Anywhere
    -0.06
    POSITIVE LOGITS
    论
    0.06
     ecc
    0.06
     nouvel
    0.06
     differing
    0.06
     coll
    0.06
     بإ
    0.06
     由
    0.06
    )=(
    0.06
     ak
    0.06
     Μη
    0.06
    Act Density 0.050%

    No Known Activations