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

    Neuronpedia

    INDEX
    Explanations

    column

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dre
    -0.07
    	ret
    -0.07
     interception
    -0.07
     remedies
    -0.07
     trad
    -0.07
     messing
    -0.06
     Likes
    -0.06
    rade
    -0.06
    がお
    -0.06
    urence
    -0.06
    POSITIVE LOGITS
     Column
    0.13
     column
    0.13
    column
    0.11
    Column
    0.10
     pillars
    0.08
    柱
    0.08
     columns
    0.08
     TableColumn
    0.08
     Bloom
    0.08
    [column
    0.08
    Act Density 0.032%

    No Known Activations