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

    Neuronpedia

    INDEX
    Explanations

    underscore

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    against
    -0.07
     TableColumn
    -0.06
    ้าหน
    -0.06
    Columns
    -0.06
     privately
    -0.06
    иля
    -0.06
    ля
    -0.06
     hoá
    -0.06
    漫画
    -0.06
    َك
    -0.06
    POSITIVE LOGITS
     WL
    0.07
     [#
    0.07
    	trace
    0.07
     Mask
    0.06
    》↵
    0.06
    ographically
    0.06
     fraudulent
    0.06
     �
    0.06
     prostitut
    0.06
     Astro
    0.06
    Act Density 0.001%

    No Known Activations