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

    Neuronpedia

    INDEX
    Explanations

    Russian language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     рамках
    -0.08
    ter
    -0.07
    .Classes
    -0.07
    -0.07
     tradicional
    -0.07
     CHF
    -0.07
     vuestro
    -0.07
     Dig
    -0.07
    mens
    -0.07
     EVT
    -0.07
    POSITIVE LOGITS
     joins
    0.09
     Joc
    0.09
     jo
    0.08
    JOY
    0.08
     tired
    0.08
     reti
    0.08
    -hi
    0.08
     dumped
    0.08
    JO
    0.07
     lettuce
    0.07
    Act Density 0.002%
    No Known Activations