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

    Neuronpedia

    INDEX
    Explanations

    say "ratio"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MSG
    -0.07
    .fileName
    -0.07
     ong
    -0.06
    ekten
    -0.06
    iring
    -0.06
     RA
    -0.06
    44
    -0.06
    종
    -0.06
    ROUTE
    -0.06
     Send
    -0.06
    POSITIVE LOGITS
    (!_
    0.07
    音
    0.07
     Municip
    0.06
    employment
    0.06
     čist
    0.06
    Actualizar
    0.06
     reinforces
    0.06
    \Catalog
    0.06
    uars
    0.06
    ักส
    0.06
    Act Density 0.003%

    No Known Activations