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

    Neuronpedia

    INDEX
    Explanations

    colon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    terní
    -0.06
    mux
    -0.06
    Lt
    -0.06
    Rail
    -0.06
     jq
    -0.06
     الاخ
    -0.06
     =
↵
    -0.06
    _fx
    -0.06
    Folders
    -0.06
    โ
    -0.06
    POSITIVE LOGITS
     склад
    0.07
    (weights
    0.07
    /sql
    0.07
    σμός
    0.07
     tableView
    0.07
    ,[
    0.06
    grave
    0.06
    abilities
    0.06
     Hend
    0.06
     surf
    0.06
    Act Density 0.004%

    No Known Activations