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

    Neuronpedia

    INDEX
    Explanations

    points

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UCK
    -0.06
    154
    -0.06
    .rcParams
    -0.06
    uck
    -0.06
    Ready
    -0.06
     Brooks
    -0.06
    об
    -0.06
    uplicate
    -0.06
     Morales
    -0.06
     Crown
    -0.06
    POSITIVE LOGITS
     Promotion
    0.06
    +offset
    0.06
     اطل
    0.06
    -component
    0.06
    typename
    0.06
     часа
    0.06
    έντρο
    0.06
     ایالات
    0.06
     neste
    0.06
    생님
    0.06
    Act Density 0.016%

    No Known Activations