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

    Neuronpedia

    INDEX
    Explanations

    Arithmetic problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fré
    -0.08
     perfection
    -0.08
    êcher
    -0.07
    Incident
    -0.07
     tenure
    -0.07
    Exceeded
    -0.07
     совершен
    -0.07
    iança
    -0.07
     exceeded
    -0.07
     coordinates
    -0.07
    POSITIVE LOGITS
     alternating
    0.13
    saldo
    0.09
     sums
    0.09
     telesc
    0.08
     altern
    0.08
    兔
    0.08
     Altern
    0.08
    resultado
    0.08
     saldo
    0.08
     cancel
    0.08
    Act Density 0.022%

    No Known Activations