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

    Neuronpedia

    INDEX
    Explanations

    The

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.64
    awtextra
    -0.63
     ANCHE
    -0.57
    brigens
    -0.52
     municipio
    -0.51
     Depor
    -0.50
    :✨
    -0.50
    DataAnnotations
    -0.50
     Hift
    -0.50
     Eſ
    -0.49
    POSITIVE LOGITS
     (
    0.60
    #+#
    0.57
    Попис
    0.56
    <bos>
    0.52
     Wikimedijinoj
    0.52
     is
    0.51
    ItemBackground
    0.51
     on
    0.50
    InjectAttribute
    0.50
    \|_{
    0.48
    Act Density 0.061%

    No Known Activations