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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tarafından
    -0.09
    Primer
    -0.08
     tərəfindən
    -0.08
     Primer
    -0.08
     দ্বারা
    -0.08
     арқылы
    -0.07
    бель
    -0.07
     мән
    -0.07
     primer
    -0.07
     referencia
    -0.07
    POSITIVE LOGITS
    조
    0.08
     storefront
    0.08
     điều
    0.08
    vue
    0.08
     کرا
    0.07
     ď
    0.07
     vanlig
    0.07
    kä
    0.07
     pav
    0.07
    Đi
    0.07
    Act Density 0.004%

    No Known Activations