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

    Neuronpedia

    INDEX
    Explanations

    mythology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     punto
    -0.07
     fian
    -0.07
    蒙
    -0.07
    但
    -0.06
    اطق
    -0.06
    cion
    -0.06
     persistence
    -0.06
    pile
    -0.06
     cancellation
    -0.06
     kk
    -0.06
    POSITIVE LOGITS
     Ron
    0.07
    (undefined
    0.07
     게시물
    0.07
     duplic
    0.06
     swell
    0.06
    .Fetch
    0.06
     treating
    0.06
     evenings
    0.06
    .confirm
    0.06
    <()>
    0.06
    Act Density 0.022%

    No Known Activations