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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    purchase
    -0.06
    год
    -0.06
     нег
    -0.06
    perature
    -0.06
     Nath
    -0.06
     przy
    -0.05
    ewear
    -0.05
     Don
    -0.05
     Clear
    -0.05
    ом
    -0.05
    POSITIVE LOGITS
    }}}
    0.07
     accumulating
    0.07
     ECB
    0.07
    await
    0.07
     Peyton
    0.06
    �
    0.06
    提升
    0.06
    atables
    0.06
    lip
    0.06
    نتاج
    0.06
    Act Density 0.001%

    No Known Activations