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

    Neuronpedia

    INDEX
    Explanations

    arithmetic calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tenter
    -0.08
     মহান
    -0.07
    iant
    -0.07
    (parameters
    -0.07
     �
    -0.07
    先进
    -0.07
     someday
    -0.07
    我们
    -0.07
    .Adv
    -0.07
    יינו
    -0.07
    POSITIVE LOGITS
     adicional
    0.09
     adicionales
    0.09
     toevo
    0.08
     alku
    0.08
    одар
    0.08
     remainder
    0.08
    mainder
    0.08
    erval
    0.08
     إضاف
    0.08
     Erd
    0.08
    Act Density 0.042%

    No Known Activations