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

    Neuronpedia

    INDEX
    Explanations

    quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     feather
    -0.07
    éfono
    -0.07
    .addTarget
    -0.07
    ?).
    -0.07
     Nhà
    -0.06
     anlaşma
    -0.06
     действие
    -0.06
    ependency
    -0.06
    뢉
    -0.06
    Deck
    -0.06
    POSITIVE LOGITS
    определ
    0.07
    )>↵
    0.07
    金华
    0.07
    .it
    0.07
    			
↵			
↵
    0.07
    Unable
    0.07
    ())↵↵
    0.07
     Mir
    0.06
     SCHOOL
    0.06
    .Key
    0.06
    Act Density 0.128%

    No Known Activations