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

    Neuronpedia

    INDEX
    Explanations

    mathematical computations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ాలి
    -0.08
     convers
    -0.08
    akur
    -0.08
    čo
    -0.08
    kode
    -0.08
     denne
    -0.08
     générations
    -0.08
    ware
    -0.07
    zei
    -0.07
     Bairro
    -0.07
    POSITIVE LOGITS
     birbir
    0.12
     서로
    0.11
     insgesamt
    0.10
     overall
    0.10
    Together
    0.10
     combining
    0.10
     juntos
    0.10
     together
    0.09
     zusammeng
    0.09
     totaling
    0.09
    Act Density 0.153%

    No Known Activations