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

    Neuronpedia

    INDEX
    Explanations

    foreign languages and names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Raff
    -0.08
     
    -0.08
     elastic
    -0.07
     
    -0.07
    invoice
    -0.07
       
    -0.07
     sparse
    -0.07
     rectangular
    -0.07
     긴
    -0.07
     détail
    -0.07
    POSITIVE LOGITS
     someday
    0.09
     আগামী
    0.09
     amea
    0.08
     beloved
    0.08
    Austin
    0.08
     бой
    0.08
     hoes
    0.08
     tomorrow
    0.08
     Guardiola
    0.08
    成为
    0.08
    Act Density 0.032%

    No Known Activations